format

pytorch · Nov 27, 2023 · 2361765 · 2361765
1 parent 9a06db6
commit 2361765
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 3 deletions.
diff --git a/examples/ppo/ppo_mujoco.py b/examples/ppo/ppo_mujoco.py
@@ -187,8 +187,9 @@ def main(cfg: "DictConfig"):  # noqa: F821
                 "train/lr": alpha * cfg_optim_lr,
                 "train/sampling_time": sampling_time,
                 "train/training_time": training_time,
-                "train/clip_epsilon": alpha * cfg_loss_clip_epsilon if
-                cfg_loss_anneal_clip_eps else cfg_loss_clip_epsilon,
+                "train/clip_epsilon": alpha * cfg_loss_clip_epsilon
+                if cfg_loss_anneal_clip_eps
+                else cfg_loss_clip_epsilon,
             }
         )
 

diff --git a/examples/ppo/utils_mujoco.py b/examples/ppo/utils_mujoco.py
@@ -24,6 +24,7 @@
 # Environment utils
 # --------------------------------------------------------------------
 
+
 def make_env(env_name="HalfCheetah-v4", device="cpu"):
     env = GymEnv(env_name, device=device)
     env = TransformedEnv(env)
@@ -71,7 +72,9 @@ def make_ppo_models_state(proof_environment):
     # Add state-independent normal scale
     policy_mlp = torch.nn.Sequential(
         policy_mlp,
-        AddStateIndependentNormalScale(proof_environment.action_spec.shape[-1], scale_lb=1e-8)
+        AddStateIndependentNormalScale(
+            proof_environment.action_spec.shape[-1], scale_lb=1e-8
+        ),
     )
 
     # Add probabilistic sampling of the actions