-
Notifications
You must be signed in to change notification settings - Fork 0
/
test.nohup
528 lines (527 loc) · 89.3 KB
/
test.nohup
1
0%|[34m [0m| 0/1000 [00:00<?, ?it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 0%|[34m [0m| 0/1000 [00:00<?, ?it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 0%|[34m [0m| 1/1000 [00:00<13:01, 1.28it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 0%|[34m [0m| 3/1000 [00:00<04:15, 3.90it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 0%|[34m [0m| 5/1000 [00:01<02:40, 6.21it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 1%|[34m [0m| 7/1000 [00:01<02:03, 8.04it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 1%|[34m [0m| 9/1000 [00:01<01:43, 9.55it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 1%|[34m [0m| 11/1000 [00:01<01:35, 10.41it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 1%|[34m▏ [0m| 13/1000 [00:01<01:27, 11.32it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 2%|[34m▏ [0m| 15/1000 [00:01<01:21, 12.03it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 2%|[34m▏ [0m| 17/1000 [00:01<01:17, 12.68it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 2%|[34m▏ [0m| 19/1000 [00:02<01:14, 13.13it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 2%|[34m▏ [0m| 21/1000 [00:02<01:12, 13.46it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 2%|[34m▏ [0m| 23/1000 [00:02<01:11, 13.75it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 2%|[34m▎ [0m| 25/1000 [00:02<01:09, 13.94it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 3%|[34m▎ [0m| 27/1000 [00:02<01:09, 14.08it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 3%|[34m▎ [0m| 29/1000 [00:02<01:08, 14.17it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 3%|[34m▎ [0m| 31/1000 [00:02<01:07, 14.35it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 3%|[34m▎ [0m| 33/1000 [00:03<01:06, 14.55it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 4%|[34m▎ [0m| 35/1000 [00:03<01:07, 14.39it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 4%|[34m▎ [0m| 37/1000 [00:03<01:07, 14.20it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 4%|[34m▍ [0m| 39/1000 [00:03<01:07, 14.17it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 4%|[34m▍ [0m| 41/1000 [00:03<01:07, 14.10it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 4%|[34m▍ [0m| 43/1000 [00:03<01:07, 14.11it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 4%|[34m▍ [0m| 45/1000 [00:03<01:07, 14.20it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 5%|[34m▍ [0m| 47/1000 [00:04<01:05, 14.47it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 5%|[34m▍ [0m| 49/1000 [00:04<01:05, 14.46it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 5%|[34m▌ [0m| 51/1000 [00:04<01:05, 14.48it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 5%|[34m▌ [0m| 53/1000 [00:04<01:04, 14.60it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 6%|[34m▌ [0m| 55/1000 [00:04<01:04, 14.66it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 6%|[34m▌ [0m| 57/1000 [00:04<01:04, 14.71it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 6%|[34m▌ [0m| 59/1000 [00:04<01:03, 14.76it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 6%|[34m▌ [0m| 61/1000 [00:04<01:03, 14.89it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 6%|[34m▋ [0m| 63/1000 [00:05<01:03, 14.79it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 6%|[34m▋ [0m| 65/1000 [00:05<01:03, 14.65it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 7%|[34m▋ [0m| 67/1000 [00:05<01:03, 14.77it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 7%|[34m▋ [0m| 69/1000 [00:05<01:02, 14.86it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 7%|[34m▋ [0m| 71/1000 [00:05<01:02, 14.90it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 7%|[34m▋ [0m| 73/1000 [00:05<01:02, 14.93it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 8%|[34m▊ [0m| 75/1000 [00:05<01:06, 13.95it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 8%|[34m▊ [0m| 77/1000 [00:06<01:05, 14.16it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 8%|[34m▊ [0m| 79/1000 [00:06<01:04, 14.25it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 8%|[34m▊ [0m| 81/1000 [00:06<01:03, 14.51it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 8%|[34m▊ [0m| 83/1000 [00:06<01:02, 14.63it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 8%|[34m▊ [0m| 85/1000 [00:06<01:03, 14.30it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 9%|[34m▊ [0m| 87/1000 [00:06<01:06, 13.69it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 9%|[34m▉ [0m| 89/1000 [00:06<01:04, 14.10it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 9%|[34m▉ [0m| 91/1000 [00:07<01:04, 14.03it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 9%|[34m▉ [0m| 93/1000 [00:07<01:03, 14.20it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 10%|[34m▉ [0m| 95/1000 [00:07<01:02, 14.47it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 10%|[34m▉ [0m| 97/1000 [00:07<01:02, 14.52it/s]> Episode 0 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 10%|[34m▉ [0m| 99/1000 [00:07<01:01, 14.64it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 10%|[34m▉ [0m| 99/1000 [00:08<01:01, 14.64it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 10%|[34m█ [0m| 101/1000 [00:08<02:11, 6.86it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 10%|[34m█ [0m| 103/1000 [00:08<01:49, 8.22it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 10%|[34m█ [0m| 105/1000 [00:08<01:33, 9.54it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 11%|[34m█ [0m| 107/1000 [00:08<01:23, 10.75it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 11%|[34m█ [0m| 109/1000 [00:08<01:15, 11.82it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 11%|[34m█ [0m| 111/1000 [00:08<01:10, 12.68it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 11%|[34m█▏ [0m| 113/1000 [00:09<01:06, 13.33it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 12%|[34m█▏ [0m| 115/1000 [00:09<01:05, 13.59it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 12%|[34m█▏ [0m| 117/1000 [00:09<01:03, 13.94it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 12%|[34m█▏ [0m| 119/1000 [00:09<01:01, 14.29it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 12%|[34m█▏ [0m| 121/1000 [00:09<01:00, 14.49it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 12%|[34m█▏ [0m| 123/1000 [00:09<00:59, 14.69it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 12%|[34m█▎ [0m| 125/1000 [00:09<00:58, 14.88it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 13%|[34m█▎ [0m| 127/1000 [00:09<00:58, 14.98it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 13%|[34m█▎ [0m| 129/1000 [00:10<00:57, 15.03it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 13%|[34m█▎ [0m| 131/1000 [00:10<00:58, 14.83it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 13%|[34m█▎ [0m| 133/1000 [00:10<00:58, 14.92it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 14%|[34m█▎ [0m| 135/1000 [00:10<00:57, 14.99it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 14%|[34m█▎ [0m| 137/1000 [00:10<00:57, 15.07it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 14%|[34m█▍ [0m| 139/1000 [00:10<00:56, 15.12it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 14%|[34m█▍ [0m| 141/1000 [00:10<00:56, 15.15it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 14%|[34m█▍ [0m| 143/1000 [00:11<00:56, 15.17it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 14%|[34m█▍ [0m| 145/1000 [00:11<00:57, 14.89it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 15%|[34m█▍ [0m| 147/1000 [00:11<00:57, 14.86it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 15%|[34m█▍ [0m| 149/1000 [00:11<00:56, 14.94it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 15%|[34m█▌ [0m| 151/1000 [00:11<00:56, 14.98it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 15%|[34m█▌ [0m| 153/1000 [00:11<00:56, 15.01it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 16%|[34m█▌ [0m| 155/1000 [00:11<00:56, 15.05it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 16%|[34m█▌ [0m| 157/1000 [00:11<00:55, 15.13it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 16%|[34m█▌ [0m| 159/1000 [00:12<00:55, 15.08it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 16%|[34m█▌ [0m| 161/1000 [00:12<00:56, 14.95it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 16%|[34m█▋ [0m| 163/1000 [00:12<00:55, 14.99it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 16%|[34m█▋ [0m| 165/1000 [00:12<00:55, 15.03it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 17%|[34m█▋ [0m| 167/1000 [00:12<00:55, 15.08it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 17%|[34m█▋ [0m| 169/1000 [00:12<00:54, 15.15it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 17%|[34m█▋ [0m| 171/1000 [00:12<00:54, 15.18it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 17%|[34m█▋ [0m| 173/1000 [00:13<00:54, 15.21it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 18%|[34m█▊ [0m| 175/1000 [00:13<00:54, 15.08it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 18%|[34m█▊ [0m| 177/1000 [00:13<00:54, 14.99it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 18%|[34m█▊ [0m| 179/1000 [00:13<00:54, 15.07it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 18%|[34m█▊ [0m| 181/1000 [00:13<00:54, 15.11it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 18%|[34m█▊ [0m| 183/1000 [00:13<00:53, 15.15it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 18%|[34m█▊ [0m| 185/1000 [00:13<00:54, 15.07it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 19%|[34m█▊ [0m| 187/1000 [00:13<00:53, 15.09it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 19%|[34m█▉ [0m| 189/1000 [00:14<00:53, 15.10it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 19%|[34m█▉ [0m| 191/1000 [00:14<00:54, 14.96it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 19%|[34m█▉ [0m| 193/1000 [00:14<00:53, 15.01it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 20%|[34m█▉ [0m| 195/1000 [00:14<00:53, 15.02it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 20%|[34m█▉ [0m| 197/1000 [00:14<00:53, 15.05it/s]> Episode 100 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 20%|[34m█▉ [0m| 199/1000 [00:14<00:53, 15.10it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 20%|[34m█▉ [0m| 199/1000 [00:15<00:53, 15.10it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 20%|[34m██ [0m| 201/1000 [00:15<01:57, 6.82it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 20%|[34m██ [0m| 203/1000 [00:15<01:37, 8.16it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 20%|[34m██ [0m| 205/1000 [00:15<01:23, 9.47it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 21%|[34m██ [0m| 207/1000 [00:15<01:15, 10.57it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 21%|[34m██ [0m| 209/1000 [00:15<01:08, 11.62it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 21%|[34m██ [0m| 211/1000 [00:16<01:03, 12.45it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 21%|[34m██▏ [0m| 213/1000 [00:16<01:00, 13.04it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 22%|[34m██▏ [0m| 215/1000 [00:16<00:57, 13.63it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 22%|[34m██▏ [0m| 217/1000 [00:16<00:55, 14.03it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 22%|[34m██▏ [0m| 219/1000 [00:16<00:54, 14.33it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 22%|[34m██▏ [0m| 221/1000 [00:16<00:53, 14.57it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 22%|[34m██▏ [0m| 223/1000 [00:16<00:52, 14.75it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 22%|[34m██▎ [0m| 225/1000 [00:17<00:53, 14.61it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 23%|[34m██▎ [0m| 227/1000 [00:17<00:54, 14.25it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 23%|[34m██▎ [0m| 229/1000 [00:17<00:54, 14.26it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 23%|[34m██▎ [0m| 231/1000 [00:17<00:53, 14.47it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 23%|[34m██▎ [0m| 233/1000 [00:17<00:53, 14.31it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 24%|[34m██▎ [0m| 235/1000 [00:17<00:53, 14.26it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 24%|[34m██▎ [0m| 237/1000 [00:17<00:52, 14.48it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 24%|[34m██▍ [0m| 239/1000 [00:18<00:52, 14.42it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 24%|[34m██▍ [0m| 241/1000 [00:18<00:53, 14.28it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 24%|[34m██▍ [0m| 243/1000 [00:18<00:53, 14.21it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 24%|[34m██▍ [0m| 245/1000 [00:18<00:53, 14.25it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 25%|[34m██▍ [0m| 247/1000 [00:18<00:53, 14.18it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 25%|[34m██▍ [0m| 249/1000 [00:18<00:52, 14.21it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 25%|[34m██▌ [0m| 251/1000 [00:18<00:53, 14.00it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 25%|[34m██▌ [0m| 253/1000 [00:19<00:52, 14.12it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 26%|[34m██▌ [0m| 255/1000 [00:19<00:52, 14.12it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 26%|[34m██▌ [0m| 257/1000 [00:19<00:52, 14.12it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 26%|[34m██▌ [0m| 259/1000 [00:19<00:52, 14.15it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 26%|[34m██▌ [0m| 261/1000 [00:19<00:52, 14.17it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 26%|[34m██▋ [0m| 263/1000 [00:19<00:52, 14.17it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 26%|[34m██▋ [0m| 265/1000 [00:19<00:51, 14.18it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 27%|[34m██▋ [0m| 267/1000 [00:20<00:51, 14.28it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 27%|[34m██▋ [0m| 269/1000 [00:20<00:51, 14.29it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 27%|[34m██▋ [0m| 271/1000 [00:20<00:51, 14.27it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 27%|[34m██▋ [0m| 273/1000 [00:20<00:50, 14.35it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 28%|[34m██▊ [0m| 275/1000 [00:20<00:50, 14.41it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 28%|[34m██▊ [0m| 277/1000 [00:20<00:50, 14.38it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 28%|[34m██▊ [0m| 279/1000 [00:20<00:49, 14.45it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 28%|[34m██▊ [0m| 281/1000 [00:20<00:49, 14.64it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 28%|[34m██▊ [0m| 283/1000 [00:21<00:48, 14.66it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 28%|[34m██▊ [0m| 285/1000 [00:21<00:50, 14.22it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 29%|[34m██▊ [0m| 287/1000 [00:21<00:49, 14.32it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 29%|[34m██▉ [0m| 289/1000 [00:21<00:49, 14.43it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 29%|[34m██▉ [0m| 291/1000 [00:21<00:50, 14.08it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 29%|[34m██▉ [0m| 293/1000 [00:21<00:52, 13.43it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 30%|[34m██▉ [0m| 295/1000 [00:21<00:51, 13.56it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 30%|[34m██▉ [0m| 297/1000 [00:22<00:52, 13.29it/s]> Episode 200 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 30%|[34m██▉ [0m| 299/1000 [00:22<00:52, 13.41it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 30%|[34m██▉ [0m| 299/1000 [00:22<00:52, 13.41it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 30%|[34m███ [0m| 301/1000 [00:22<01:47, 6.50it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 30%|[34m███ [0m| 303/1000 [00:23<01:29, 7.78it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 30%|[34m███ [0m| 305/1000 [00:23<01:17, 9.02it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 31%|[34m███ [0m| 307/1000 [00:23<01:08, 10.19it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 31%|[34m███ [0m| 309/1000 [00:23<01:02, 10.98it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 31%|[34m███ [0m| 311/1000 [00:23<01:00, 11.38it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 31%|[34m███▏ [0m| 313/1000 [00:23<00:56, 12.05it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 32%|[34m███▏ [0m| 315/1000 [00:23<00:54, 12.65it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 32%|[34m███▏ [0m| 317/1000 [00:24<00:52, 13.08it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 32%|[34m███▏ [0m| 319/1000 [00:24<00:51, 13.25it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 32%|[34m███▏ [0m| 321/1000 [00:24<00:51, 13.30it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 32%|[34m███▏ [0m| 323/1000 [00:24<00:50, 13.37it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 32%|[34m███▎ [0m| 325/1000 [00:24<00:49, 13.54it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 33%|[34m███▎ [0m| 327/1000 [00:24<00:49, 13.68it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 33%|[34m███▎ [0m| 329/1000 [00:24<00:48, 13.78it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 33%|[34m███▎ [0m| 331/1000 [00:25<00:48, 13.80it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 33%|[34m███▎ [0m| 333/1000 [00:25<00:48, 13.79it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 34%|[34m███▎ [0m| 335/1000 [00:25<00:48, 13.83it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 34%|[34m███▎ [0m| 337/1000 [00:25<00:47, 13.88it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 34%|[34m███▍ [0m| 339/1000 [00:25<00:47, 13.91it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 34%|[34m███▍ [0m| 341/1000 [00:25<00:47, 13.92it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 34%|[34m███▍ [0m| 343/1000 [00:26<00:47, 13.94it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 34%|[34m███▍ [0m| 345/1000 [00:26<00:46, 14.01it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 35%|[34m███▍ [0m| 347/1000 [00:26<00:47, 13.85it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 35%|[34m███▍ [0m| 349/1000 [00:26<00:46, 13.93it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 35%|[34m███▌ [0m| 351/1000 [00:26<00:46, 14.01it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 35%|[34m███▌ [0m| 353/1000 [00:26<00:46, 14.05it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 36%|[34m███▌ [0m| 355/1000 [00:26<00:45, 14.10it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 36%|[34m███▌ [0m| 357/1000 [00:27<00:45, 14.12it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 36%|[34m███▌ [0m| 359/1000 [00:27<00:46, 13.88it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 36%|[34m███▌ [0m| 361/1000 [00:27<00:46, 13.82it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 36%|[34m███▋ [0m| 363/1000 [00:27<00:45, 13.96it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 36%|[34m███▋ [0m| 365/1000 [00:27<00:45, 14.03it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 37%|[34m███▋ [0m| 367/1000 [00:27<00:44, 14.09it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 37%|[34m███▋ [0m| 369/1000 [00:27<00:44, 14.15it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 37%|[34m███▋ [0m| 371/1000 [00:28<00:44, 14.09it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 37%|[34m███▋ [0m| 373/1000 [00:28<00:44, 14.06it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 38%|[34m███▊ [0m| 375/1000 [00:28<00:45, 13.85it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 38%|[34m███▊ [0m| 377/1000 [00:28<00:44, 14.01it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 38%|[34m███▊ [0m| 379/1000 [00:28<00:44, 14.08it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 38%|[34m███▊ [0m| 381/1000 [00:28<00:43, 14.09it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 38%|[34m███▊ [0m| 383/1000 [00:28<00:43, 14.16it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 38%|[34m███▊ [0m| 385/1000 [00:28<00:42, 14.34it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 39%|[34m███▊ [0m| 387/1000 [00:29<00:42, 14.35it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 39%|[34m███▉ [0m| 389/1000 [00:29<00:42, 14.27it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 39%|[34m███▉ [0m| 391/1000 [00:29<00:42, 14.34it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 39%|[34m███▉ [0m| 393/1000 [00:29<00:42, 14.23it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 40%|[34m███▉ [0m| 395/1000 [00:29<00:42, 14.27it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 40%|[34m███▉ [0m| 397/1000 [00:29<00:42, 14.30it/s]> Episode 300 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 40%|[34m███▉ [0m| 399/1000 [00:29<00:41, 14.43it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 40%|[34m███▉ [0m| 399/1000 [00:30<00:41, 14.43it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 40%|[34m████ [0m| 401/1000 [00:30<01:29, 6.66it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 40%|[34m████ [0m| 403/1000 [00:30<01:15, 7.95it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 40%|[34m████ [0m| 405/1000 [00:30<01:05, 9.12it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 41%|[34m████ [0m| 407/1000 [00:31<00:57, 10.30it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 41%|[34m████ [0m| 409/1000 [00:31<00:53, 11.10it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 41%|[34m████ [0m| 411/1000 [00:31<00:49, 11.85it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 41%|[34m████▏ [0m| 413/1000 [00:31<00:46, 12.56it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 42%|[34m████▏ [0m| 415/1000 [00:31<00:44, 13.04it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 42%|[34m████▏ [0m| 417/1000 [00:31<00:43, 13.35it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 42%|[34m████▏ [0m| 419/1000 [00:31<00:42, 13.70it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 42%|[34m████▏ [0m| 421/1000 [00:32<00:41, 14.07it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 42%|[34m████▏ [0m| 423/1000 [00:32<00:40, 14.22it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 42%|[34m████▎ [0m| 425/1000 [00:32<00:40, 14.18it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 43%|[34m████▎ [0m| 427/1000 [00:32<00:39, 14.33it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 43%|[34m████▎ [0m| 429/1000 [00:32<00:40, 14.23it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 43%|[34m████▎ [0m| 431/1000 [00:32<00:39, 14.28it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 43%|[34m████▎ [0m| 433/1000 [00:32<00:39, 14.24it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 44%|[34m████▎ [0m| 435/1000 [00:33<00:39, 14.42it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 44%|[34m████▎ [0m| 437/1000 [00:33<00:40, 14.07it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 44%|[34m████▍ [0m| 439/1000 [00:33<00:40, 13.99it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 44%|[34m████▍ [0m| 441/1000 [00:33<00:39, 14.11it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 44%|[34m████▍ [0m| 443/1000 [00:33<00:39, 14.00it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 44%|[34m████▍ [0m| 445/1000 [00:33<00:39, 14.12it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 45%|[34m████▍ [0m| 447/1000 [00:33<00:39, 14.13it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 45%|[34m████▍ [0m| 449/1000 [00:34<00:38, 14.27it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 45%|[34m████▌ [0m| 451/1000 [00:34<00:38, 14.36it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 45%|[34m████▌ [0m| 453/1000 [00:34<00:38, 14.20it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 46%|[34m████▌ [0m| 455/1000 [00:34<00:38, 14.09it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 46%|[34m████▌ [0m| 457/1000 [00:34<00:38, 14.03it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 46%|[34m████▌ [0m| 459/1000 [00:34<00:38, 14.07it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 46%|[34m████▌ [0m| 461/1000 [00:34<00:38, 13.98it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 46%|[34m████▋ [0m| 463/1000 [00:35<00:38, 14.09it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 46%|[34m████▋ [0m| 465/1000 [00:35<00:38, 14.06it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 47%|[34m████▋ [0m| 467/1000 [00:35<00:38, 13.98it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 47%|[34m████▋ [0m| 469/1000 [00:35<00:37, 13.99it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 47%|[34m████▋ [0m| 471/1000 [00:35<00:37, 14.03it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 47%|[34m████▋ [0m| 473/1000 [00:35<00:37, 14.09it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 48%|[34m████▊ [0m| 475/1000 [00:35<00:37, 14.12it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 48%|[34m████▊ [0m| 477/1000 [00:35<00:36, 14.18it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 48%|[34m████▊ [0m| 479/1000 [00:36<00:36, 14.17it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 48%|[34m████▊ [0m| 481/1000 [00:36<00:36, 14.12it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 48%|[34m████▊ [0m| 483/1000 [00:36<00:36, 14.24it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 48%|[34m████▊ [0m| 485/1000 [00:36<00:36, 14.21it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 49%|[34m████▊ [0m| 487/1000 [00:36<00:36, 14.11it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 49%|[34m████▉ [0m| 489/1000 [00:36<00:36, 14.19it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 49%|[34m████▉ [0m| 491/1000 [00:36<00:35, 14.27it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 49%|[34m████▉ [0m| 493/1000 [00:37<00:36, 13.92it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 50%|[34m████▉ [0m| 495/1000 [00:37<00:36, 13.92it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 50%|[34m████▉ [0m| 497/1000 [00:37<00:35, 14.12it/s]> Episode 400 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 50%|[34m████▉ [0m| 499/1000 [00:37<00:35, 14.05it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 50%|[34m████▉ [0m| 499/1000 [00:38<00:35, 14.05it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 50%|[34m█████ [0m| 501/1000 [00:38<01:16, 6.56it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 50%|[34m█████ [0m| 503/1000 [00:38<01:03, 7.85it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 50%|[34m█████ [0m| 505/1000 [00:38<00:55, 8.97it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 51%|[34m█████ [0m| 507/1000 [00:38<00:49, 10.01it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 51%|[34m█████ [0m| 509/1000 [00:38<00:45, 10.88it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 51%|[34m█████ [0m| 511/1000 [00:38<00:41, 11.66it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 51%|[34m█████▏ [0m| 513/1000 [00:39<00:39, 12.29it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 52%|[34m█████▏ [0m| 515/1000 [00:39<00:38, 12.72it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 52%|[34m█████▏ [0m| 517/1000 [00:39<00:37, 13.01it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 52%|[34m█████▏ [0m| 519/1000 [00:39<00:36, 13.26it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 52%|[34m█████▏ [0m| 521/1000 [00:39<00:36, 13.19it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 52%|[34m█████▏ [0m| 523/1000 [00:39<00:35, 13.36it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 52%|[34m█████▎ [0m| 525/1000 [00:40<00:36, 13.05it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 53%|[34m█████▎ [0m| 527/1000 [00:40<00:38, 12.37it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 53%|[34m█████▎ [0m| 529/1000 [00:40<00:38, 12.27it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 53%|[34m█████▎ [0m| 531/1000 [00:40<00:40, 11.61it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 53%|[34m█████▎ [0m| 533/1000 [00:40<00:39, 11.91it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 54%|[34m█████▎ [0m| 535/1000 [00:40<00:37, 12.41it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 54%|[34m█████▎ [0m| 537/1000 [00:41<00:36, 12.55it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 54%|[34m█████▍ [0m| 539/1000 [00:41<00:36, 12.77it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 54%|[34m█████▍ [0m| 541/1000 [00:41<00:36, 12.68it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 54%|[34m█████▍ [0m| 543/1000 [00:41<00:35, 12.71it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 55%|[34m█████▍ [0m| 545/1000 [00:41<00:36, 12.37it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 55%|[34m█████▍ [0m| 547/1000 [00:41<00:40, 11.24it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 55%|[34m█████▍ [0m| 549/1000 [00:42<00:41, 10.75it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 55%|[34m█████▌ [0m| 551/1000 [00:42<00:42, 10.63it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 55%|[34m█████▌ [0m| 553/1000 [00:42<00:39, 11.26it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 56%|[34m█████▌ [0m| 555/1000 [00:42<00:38, 11.56it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 56%|[34m█████▌ [0m| 557/1000 [00:42<00:38, 11.60it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 56%|[34m█████▌ [0m| 559/1000 [00:42<00:42, 10.40it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 56%|[34m█████▌ [0m| 561/1000 [00:43<00:47, 9.26it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 56%|[34m█████▌ [0m| 562/1000 [00:43<00:50, 8.62it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 56%|[34m█████▋ [0m| 563/1000 [00:43<00:53, 8.23it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 56%|[34m█████▋ [0m| 565/1000 [00:43<00:48, 9.05it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 57%|[34m█████▋ [0m| 566/1000 [00:43<00:50, 8.66it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 57%|[34m█████▋ [0m| 567/1000 [00:43<00:50, 8.57it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 57%|[34m█████▋ [0m| 568/1000 [00:44<00:50, 8.50it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 57%|[34m█████▋ [0m| 570/1000 [00:44<00:46, 9.33it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 57%|[34m█████▋ [0m| 572/1000 [00:44<00:40, 10.50it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 57%|[34m█████▋ [0m| 574/1000 [00:44<00:40, 10.56it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 58%|[34m█████▊ [0m| 576/1000 [00:44<00:40, 10.41it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 58%|[34m█████▊ [0m| 578/1000 [00:45<00:42, 10.00it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 58%|[34m█████▊ [0m| 580/1000 [00:45<00:44, 9.39it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 58%|[34m█████▊ [0m| 581/1000 [00:45<00:45, 9.21it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 58%|[34m█████▊ [0m| 582/1000 [00:45<00:46, 8.90it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 58%|[34m█████▊ [0m| 583/1000 [00:45<00:50, 8.29it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 58%|[34m█████▊ [0m| 584/1000 [00:45<00:52, 8.00it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 59%|[34m█████▊ [0m| 586/1000 [00:45<00:44, 9.36it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 59%|[34m█████▉ [0m| 588/1000 [00:46<00:40, 10.09it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 59%|[34m█████▉ [0m| 590/1000 [00:46<00:38, 10.52it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 59%|[34m█████▉ [0m| 592/1000 [00:46<00:44, 9.22it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 59%|[34m█████▉ [0m| 593/1000 [00:46<00:44, 9.13it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 59%|[34m█████▉ [0m| 594/1000 [00:46<00:43, 9.23it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 60%|[34m█████▉ [0m| 595/1000 [00:46<00:47, 8.59it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 60%|[34m█████▉ [0m| 596/1000 [00:47<00:53, 7.62it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 60%|[34m█████▉ [0m| 597/1000 [00:47<00:57, 7.04it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 60%|[34m█████▉ [0m| 598/1000 [00:47<00:58, 6.89it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 60%|[34m█████▉ [0m| 599/1000 [00:47<00:59, 6.75it/s]> Episode 500 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 60%|[34m██████ [0m| 600/1000 [00:47<00:54, 7.32it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 60%|[34m██████ [0m| 600/1000 [00:48<00:54, 7.32it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 60%|[34m██████ [0m| 601/1000 [00:48<02:15, 2.94it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 60%|[34m██████ [0m| 603/1000 [00:48<01:29, 4.41it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 60%|[34m██████ [0m| 605/1000 [00:48<01:06, 5.90it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 61%|[34m██████ [0m| 607/1000 [00:49<00:56, 6.98it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 61%|[34m██████ [0m| 609/1000 [00:49<00:46, 8.38it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 61%|[34m██████ [0m| 611/1000 [00:49<00:40, 9.62it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 61%|[34m██████▏ [0m| 613/1000 [00:49<00:37, 10.44it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 62%|[34m██████▏ [0m| 615/1000 [00:49<00:36, 10.57it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 62%|[34m██████▏ [0m| 617/1000 [00:49<00:36, 10.38it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 62%|[34m██████▏ [0m| 619/1000 [00:50<00:38, 9.80it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 62%|[34m██████▏ [0m| 621/1000 [00:50<00:39, 9.64it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 62%|[34m██████▏ [0m| 623/1000 [00:50<00:39, 9.66it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 62%|[34m██████▏ [0m| 624/1000 [00:50<00:39, 9.61it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 62%|[34m██████▎ [0m| 625/1000 [00:50<00:40, 9.26it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 63%|[34m██████▎ [0m| 626/1000 [00:50<00:40, 9.33it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 63%|[34m██████▎ [0m| 627/1000 [00:51<00:40, 9.28it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 63%|[34m██████▎ [0m| 628/1000 [00:51<00:39, 9.31it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 63%|[34m██████▎ [0m| 629/1000 [00:51<00:43, 8.58it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 63%|[34m██████▎ [0m| 630/1000 [00:51<00:41, 8.91it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 63%|[34m██████▎ [0m| 632/1000 [00:51<00:35, 10.46it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 63%|[34m██████▎ [0m| 634/1000 [00:51<00:32, 11.39it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 64%|[34m██████▎ [0m| 636/1000 [00:51<00:31, 11.58it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 64%|[34m██████▍ [0m| 638/1000 [00:52<00:33, 10.90it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 64%|[34m██████▍ [0m| 640/1000 [00:52<00:32, 11.00it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 64%|[34m██████▍ [0m| 642/1000 [00:52<00:32, 10.93it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 64%|[34m██████▍ [0m| 644/1000 [00:52<00:33, 10.75it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 65%|[34m██████▍ [0m| 646/1000 [00:52<00:33, 10.71it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 65%|[34m██████▍ [0m| 648/1000 [00:52<00:34, 10.24it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 65%|[34m██████▌ [0m| 650/1000 [00:53<00:34, 10.27it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 65%|[34m██████▌ [0m| 652/1000 [00:53<00:34, 10.14it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 65%|[34m██████▌ [0m| 654/1000 [00:53<00:32, 10.54it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 66%|[34m██████▌ [0m| 656/1000 [00:53<00:31, 10.86it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 66%|[34m██████▌ [0m| 658/1000 [00:53<00:34, 10.01it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 66%|[34m██████▌ [0m| 660/1000 [00:54<00:33, 10.25it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 66%|[34m██████▌ [0m| 662/1000 [00:54<00:33, 10.23it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 66%|[34m██████▋ [0m| 664/1000 [00:54<00:33, 10.13it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 67%|[34m██████▋ [0m| 666/1000 [00:54<00:36, 9.21it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 67%|[34m██████▋ [0m| 667/1000 [00:54<00:37, 8.79it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 67%|[34m██████▋ [0m| 668/1000 [00:55<00:38, 8.67it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 67%|[34m██████▋ [0m| 669/1000 [00:55<00:37, 8.88it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 67%|[34m██████▋ [0m| 670/1000 [00:55<00:36, 9.08it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 67%|[34m██████▋ [0m| 672/1000 [00:55<00:36, 9.04it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 67%|[34m██████▋ [0m| 673/1000 [00:55<00:36, 8.97it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 68%|[34m██████▊ [0m| 675/1000 [00:55<00:31, 10.18it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 68%|[34m██████▊ [0m| 677/1000 [00:55<00:28, 11.17it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 68%|[34m██████▊ [0m| 679/1000 [00:56<00:27, 11.51it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 68%|[34m██████▊ [0m| 681/1000 [00:56<00:26, 12.08it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 68%|[34m██████▊ [0m| 683/1000 [00:56<00:26, 12.03it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 68%|[34m██████▊ [0m| 685/1000 [00:56<00:25, 12.22it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 69%|[34m██████▊ [0m| 687/1000 [00:56<00:24, 12.54it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 69%|[34m██████▉ [0m| 689/1000 [00:56<00:24, 12.83it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 69%|[34m██████▉ [0m| 691/1000 [00:57<00:24, 12.62it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 69%|[34m██████▉ [0m| 693/1000 [00:57<00:23, 12.83it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 70%|[34m██████▉ [0m| 695/1000 [00:57<00:23, 12.91it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 70%|[34m██████▉ [0m| 697/1000 [00:57<00:22, 13.28it/s]> Episode 600 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 70%|[34m██████▉ [0m| 699/1000 [00:57<00:21, 13.71it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 70%|[34m██████▉ [0m| 699/1000 [00:58<00:21, 13.71it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 70%|[34m███████ [0m| 701/1000 [00:58<00:46, 6.42it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 70%|[34m███████ [0m| 703/1000 [00:58<00:38, 7.66it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 70%|[34m███████ [0m| 705/1000 [00:58<00:33, 8.86it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 71%|[34m███████ [0m| 707/1000 [00:58<00:29, 9.99it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 71%|[34m███████ [0m| 709/1000 [00:58<00:26, 10.91it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 71%|[34m███████ [0m| 711/1000 [00:59<00:24, 11.57it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 71%|[34m███████▏ [0m| 713/1000 [00:59<00:23, 12.15it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 72%|[34m███████▏ [0m| 715/1000 [00:59<00:22, 12.74it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 72%|[34m███████▏ [0m| 717/1000 [00:59<00:21, 13.13it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 72%|[34m███████▏ [0m| 719/1000 [00:59<00:20, 13.48it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 72%|[34m███████▏ [0m| 721/1000 [00:59<00:20, 13.56it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 72%|[34m███████▏ [0m| 723/1000 [00:59<00:20, 13.59it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 72%|[34m███████▎ [0m| 725/1000 [01:00<00:20, 13.67it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 73%|[34m███████▎ [0m| 727/1000 [01:00<00:20, 13.62it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 73%|[34m███████▎ [0m| 729/1000 [01:00<00:19, 13.80it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 73%|[34m███████▎ [0m| 731/1000 [01:00<00:19, 13.90it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 73%|[34m███████▎ [0m| 733/1000 [01:00<00:19, 13.99it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 74%|[34m███████▎ [0m| 735/1000 [01:00<00:18, 14.16it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 74%|[34m███████▎ [0m| 737/1000 [01:00<00:18, 14.31it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 74%|[34m███████▍ [0m| 739/1000 [01:01<00:18, 14.22it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 74%|[34m███████▍ [0m| 741/1000 [01:01<00:18, 14.25it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 74%|[34m███████▍ [0m| 743/1000 [01:01<00:17, 14.30it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 74%|[34m███████▍ [0m| 745/1000 [01:01<00:17, 14.18it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 75%|[34m███████▍ [0m| 747/1000 [01:01<00:17, 14.20it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 75%|[34m███████▍ [0m| 749/1000 [01:01<00:17, 14.30it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 75%|[34m███████▌ [0m| 751/1000 [01:01<00:17, 14.24it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 75%|[34m███████▌ [0m| 753/1000 [01:01<00:17, 14.16it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 76%|[34m███████▌ [0m| 755/1000 [01:02<00:17, 14.14it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 76%|[34m███████▌ [0m| 757/1000 [01:02<00:17, 14.15it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 76%|[34m███████▌ [0m| 759/1000 [01:02<00:17, 14.01it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 76%|[34m███████▌ [0m| 761/1000 [01:02<00:17, 14.05it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 76%|[34m███████▋ [0m| 763/1000 [01:02<00:16, 14.10it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 76%|[34m███████▋ [0m| 765/1000 [01:02<00:16, 13.95it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 77%|[34m███████▋ [0m| 767/1000 [01:02<00:16, 13.92it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 77%|[34m███████▋ [0m| 769/1000 [01:03<00:17, 13.50it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 77%|[34m███████▋ [0m| 771/1000 [01:03<00:16, 13.48it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 77%|[34m███████▋ [0m| 773/1000 [01:03<00:16, 13.55it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 78%|[34m███████▊ [0m| 775/1000 [01:03<00:16, 13.59it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 78%|[34m███████▊ [0m| 777/1000 [01:03<00:16, 13.51it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 78%|[34m███████▊ [0m| 779/1000 [01:03<00:16, 13.68it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 78%|[34m███████▊ [0m| 781/1000 [01:04<00:15, 13.77it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 78%|[34m███████▊ [0m| 783/1000 [01:04<00:15, 13.73it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 78%|[34m███████▊ [0m| 785/1000 [01:04<00:15, 13.53it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 79%|[34m███████▊ [0m| 787/1000 [01:04<00:15, 13.55it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 79%|[34m███████▉ [0m| 789/1000 [01:04<00:15, 13.73it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 79%|[34m███████▉ [0m| 791/1000 [01:04<00:15, 13.83it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 79%|[34m███████▉ [0m| 793/1000 [01:04<00:15, 13.44it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 80%|[34m███████▉ [0m| 795/1000 [01:05<00:15, 13.49it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 80%|[34m███████▉ [0m| 797/1000 [01:05<00:14, 13.73it/s]> Episode 700 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 80%|[34m███████▉ [0m| 799/1000 [01:05<00:15, 13.23it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 80%|[34m███████▉ [0m| 799/1000 [01:06<00:15, 13.23it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 80%|[34m████████ [0m| 801/1000 [01:06<00:33, 5.87it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 80%|[34m████████ [0m| 803/1000 [01:06<00:28, 6.99it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 80%|[34m████████ [0m| 805/1000 [01:06<00:23, 8.22it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 81%|[34m████████ [0m| 807/1000 [01:06<00:20, 9.43it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 81%|[34m████████ [0m| 809/1000 [01:06<00:18, 10.51it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 81%|[34m████████ [0m| 811/1000 [01:06<00:16, 11.38it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 81%|[34m████████▏ [0m| 813/1000 [01:07<00:15, 12.12it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 82%|[34m████████▏ [0m| 815/1000 [01:07<00:14, 12.63it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 82%|[34m████████▏ [0m| 817/1000 [01:07<00:13, 13.15it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 82%|[34m████████▏ [0m| 819/1000 [01:07<00:13, 13.50it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 82%|[34m████████▏ [0m| 821/1000 [01:07<00:13, 13.60it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 82%|[34m████████▏ [0m| 823/1000 [01:07<00:12, 13.88it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 82%|[34m████████▎ [0m| 825/1000 [01:07<00:12, 14.05it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 83%|[34m████████▎ [0m| 827/1000 [01:07<00:12, 14.12it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 83%|[34m████████▎ [0m| 829/1000 [01:08<00:12, 14.15it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 83%|[34m████████▎ [0m| 831/1000 [01:08<00:12, 13.50it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 83%|[34m████████▎ [0m| 833/1000 [01:08<00:12, 13.70it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 84%|[34m████████▎ [0m| 835/1000 [01:08<00:11, 13.87it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 84%|[34m████████▎ [0m| 837/1000 [01:08<00:11, 13.92it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 84%|[34m████████▍ [0m| 839/1000 [01:08<00:11, 14.09it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 84%|[34m████████▍ [0m| 841/1000 [01:09<00:11, 14.04it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 84%|[34m████████▍ [0m| 843/1000 [01:09<00:11, 14.08it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 84%|[34m████████▍ [0m| 845/1000 [01:09<00:10, 14.22it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 85%|[34m████████▍ [0m| 847/1000 [01:09<00:10, 14.44it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 85%|[34m████████▍ [0m| 849/1000 [01:09<00:10, 14.42it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 85%|[34m████████▌ [0m| 851/1000 [01:09<00:10, 14.28it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 85%|[34m████████▌ [0m| 853/1000 [01:09<00:10, 14.23it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 86%|[34m████████▌ [0m| 855/1000 [01:09<00:10, 14.25it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 86%|[34m████████▌ [0m| 857/1000 [01:10<00:10, 14.21it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 86%|[34m████████▌ [0m| 859/1000 [01:10<00:09, 14.44it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 86%|[34m████████▌ [0m| 861/1000 [01:10<00:09, 14.61it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 86%|[34m████████▋ [0m| 863/1000 [01:10<00:09, 14.62it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 86%|[34m████████▋ [0m| 865/1000 [01:10<00:09, 14.45it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 87%|[34m████████▋ [0m| 867/1000 [01:10<00:09, 14.43it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 87%|[34m████████▋ [0m| 869/1000 [01:10<00:09, 14.41it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 87%|[34m████████▋ [0m| 871/1000 [01:11<00:08, 14.36it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 87%|[34m████████▋ [0m| 873/1000 [01:11<00:08, 14.46it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 88%|[34m████████▊ [0m| 875/1000 [01:11<00:08, 14.61it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 88%|[34m████████▊ [0m| 877/1000 [01:11<00:08, 14.63it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 88%|[34m████████▊ [0m| 879/1000 [01:11<00:08, 14.54it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 88%|[34m████████▊ [0m| 881/1000 [01:11<00:08, 14.17it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 88%|[34m████████▊ [0m| 883/1000 [01:11<00:08, 14.25it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 88%|[34m████████▊ [0m| 885/1000 [01:12<00:08, 14.18it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 89%|[34m████████▊ [0m| 887/1000 [01:12<00:07, 14.21it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 89%|[34m████████▉ [0m| 889/1000 [01:12<00:07, 14.26it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 89%|[34m████████▉ [0m| 891/1000 [01:12<00:07, 14.23it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 89%|[34m████████▉ [0m| 893/1000 [01:12<00:07, 14.18it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 90%|[34m████████▉ [0m| 895/1000 [01:12<00:07, 14.11it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 90%|[34m████████▉ [0m| 897/1000 [01:12<00:07, 14.17it/s]> Episode 800 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 90%|[34m████████▉ [0m| 899/1000 [01:13<00:07, 13.96it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 90%|[34m████████▉ [0m| 899/1000 [01:13<00:07, 13.96it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 90%|[34m█████████ [0m| 901/1000 [01:13<00:15, 6.39it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 90%|[34m█████████ [0m| 903/1000 [01:13<00:12, 7.67it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 90%|[34m█████████ [0m| 905/1000 [01:14<00:10, 8.90it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 91%|[34m█████████ [0m| 907/1000 [01:14<00:09, 10.04it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 91%|[34m█████████ [0m| 909/1000 [01:14<00:08, 11.03it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 91%|[34m█████████ [0m| 911/1000 [01:14<00:07, 11.86it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 91%|[34m█████████▏[0m| 913/1000 [01:14<00:06, 12.52it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 92%|[34m█████████▏[0m| 915/1000 [01:14<00:06, 12.93it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 92%|[34m█████████▏[0m| 917/1000 [01:14<00:06, 13.27it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 92%|[34m█████████▏[0m| 919/1000 [01:15<00:05, 13.54it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 92%|[34m█████████▏[0m| 921/1000 [01:15<00:05, 13.80it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 92%|[34m█████████▏[0m| 923/1000 [01:15<00:05, 14.01it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 92%|[34m█████████▎[0m| 925/1000 [01:15<00:05, 14.12it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 93%|[34m█████████▎[0m| 927/1000 [01:15<00:05, 14.16it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 93%|[34m█████████▎[0m| 929/1000 [01:15<00:05, 14.13it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 93%|[34m█████████▎[0m| 931/1000 [01:15<00:04, 14.22it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 93%|[34m█████████▎[0m| 933/1000 [01:16<00:04, 14.26it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 94%|[34m█████████▎[0m| 935/1000 [01:16<00:04, 14.05it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 94%|[34m█████████▎[0m| 937/1000 [01:16<00:04, 14.33it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 94%|[34m█████████▍[0m| 939/1000 [01:16<00:04, 14.51it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 94%|[34m█████████▍[0m| 941/1000 [01:16<00:04, 14.49it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 94%|[34m█████████▍[0m| 943/1000 [01:16<00:03, 14.36it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 94%|[34m█████████▍[0m| 945/1000 [01:16<00:03, 14.35it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 95%|[34m█████████▍[0m| 947/1000 [01:16<00:03, 14.39it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 95%|[34m█████████▍[0m| 949/1000 [01:17<00:03, 14.31it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 95%|[34m█████████▌[0m| 951/1000 [01:17<00:03, 14.40it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 95%|[34m█████████▌[0m| 953/1000 [01:17<00:03, 14.57it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 96%|[34m█████████▌[0m| 955/1000 [01:17<00:03, 14.54it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 96%|[34m█████████▌[0m| 957/1000 [01:17<00:02, 14.48it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 96%|[34m█████████▌[0m| 959/1000 [01:17<00:02, 13.77it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 96%|[34m█████████▌[0m| 961/1000 [01:17<00:02, 13.95it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 96%|[34m█████████▋[0m| 963/1000 [01:18<00:02, 13.93it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 96%|[34m█████████▋[0m| 965/1000 [01:18<00:02, 14.21it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 97%|[34m█████████▋[0m| 967/1000 [01:18<00:02, 14.42it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 97%|[34m█████████▋[0m| 969/1000 [01:18<00:02, 14.41it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 97%|[34m█████████▋[0m| 971/1000 [01:18<00:02, 14.38it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 97%|[34m█████████▋[0m| 973/1000 [01:18<00:01, 14.31it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 98%|[34m█████████▊[0m| 975/1000 [01:18<00:01, 14.45it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 98%|[34m█████████▊[0m| 977/1000 [01:19<00:01, 14.35it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 98%|[34m█████████▊[0m| 979/1000 [01:19<00:01, 14.21it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 98%|[34m█████████▊[0m| 981/1000 [01:19<00:01, 13.95it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 98%|[34m█████████▊[0m| 983/1000 [01:19<00:01, 13.85it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 98%|[34m█████████▊[0m| 985/1000 [01:19<00:01, 14.00it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 99%|[34m█████████▊[0m| 987/1000 [01:19<00:00, 14.07it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 99%|[34m█████████▉[0m| 989/1000 [01:19<00:00, 14.25it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 99%|[34m█████████▉[0m| 991/1000 [01:20<00:00, 14.18it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 99%|[34m█████████▉[0m| 993/1000 [01:20<00:00, 14.26it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 100%|[34m█████████▉[0m| 995/1000 [01:20<00:00, 14.39it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 100%|[34m█████████▉[0m| 997/1000 [01:20<00:00, 14.50it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 100%|[34m█████████▉[0m| 999/1000 [01:20<00:00, 14.46it/s]> Episode 900 | Stay 0.00 | agent -386.62 | optimal 432.80 | score -89.33%: 100%|[34m██████████[0m| 1000/1000 [01:20<00:00, 12.39it/s]