Feature/algorithm description

README.md

@@ -106,12 +106,13 @@ python main.py --sync --config config.ppo.cartpole --train.num_workers 8
 
 ## :page_facing_up: Documentation
 
+- [Algorithm Descriptions](./docs/Algorithm_Descriptions.md)
+- [Benchmark](https://petite-balance-8cb.notion.site/Benchmark-09684f1adf764c84a5a331cb5690544f)
 - [Distributed Architecture](./docs/Distributed_Architecture.md)
-- [Role of Managers](./jorldy/manager/README.md)
 - [List of Contents](./docs/List_of_Contents.md)
 - [Naming Convention](./docs/Naming_convention.md)
-- [Benchmark](https://petite-balance-8cb.notion.site/Benchmark-09684f1adf764c84a5a331cb5690544f)
 - [Reference](./docs/Reference.md)
+- [Role of Managers](./jorldy/manager/README.md)
 
 
 ## :busts_in_silhouette: Contributors

docs/Algorithm_Descriptions.md

@@ -0,0 +1,43 @@
+# Algorithm Descriptions
+
+:fire: [REINFORCE](./Algorithm_Descriptions/REINFORCE.pdf)
+
+:seedling: [DQN(Deep Q-Network)](./Algorithm_Descriptions/DQN.pdf)
+
+:flight_departure: [DDQN(Double_DQN)](./Algorithm_Descriptions/DDQN.pdf)
+
+:crossed_swords: [Dueling DQN](./Algorithm_Descriptions/Dueling_DQN.pdf)
+
+:medal_sports: [PER(Prioritized_Experience_Replay)](./Algorithm_Descriptions/PER.pdf)
+
+:ocean: [Noisy Network](./Algorithm_Descriptions/Noisy_Network.pdf)
+
+:slot_machine: [C51](./Algorithm_Descriptions/C51.pdf)
+
+:rainbow: [Rainbow DQN](./Algorithm_Descriptions/Rainbow_DQN.pdf)
+
+:vampire: [Munchausen RL](./Algorithm_Descriptions/Munchausen-RL.pdf)
+
+:game_die: [QR-DQN(Quantile_Regression_DQN)](./Algorithm_Descriptions/QR-DQN.pdf)
+
+:bar_chart: [IQN(Implicit_Quantile_Network)](./Algorithm_Descriptions/IQN.pdf)
+
+:family: [APE-X](./Algorithm_Descriptions/APE-X.pdf)
+
+:robot: [R2D2](./Algorithm_Descriptions/R2D2.pdf)
+
+:palm_tree: [DDPG(Deep_Deterministic_Policy_Gradient)](./Algorithm_Descriptions/DDPG.pdf)
+
+:hourglass_flowing_sand: [TD3(Twin_Delayed_DDPG)](./Algorithm_Descriptions/TD3.pdf)
+
+:cyclone: [PPO(Proximal_Policy_Optimization)](./Algorithm_Descriptions/PPO.pdf)
+
+:flying_saucer:	[SAC(Soft_Actor-Critic)](./Algorithm_Descriptions/SAC.pdf)
+
+:baseball: [MPO(Maximum_a_Posteriori_Policy_Optimization)](./Algorithm_Descriptions/MPO.pdf)
+
+:softball: [V-MPO(On-Policy Maximum a Posteriori Policy Optimization)](./Algorithm_Descriptions/V-MPO.pdf)
+
+:grey_question: [ICM(Intrinsic Curiosity Module)](./Algorithm_Descriptions/ICM.pdf)
+
+:question: [RND(Random Network Distillation)](./Algorithm_Descriptions/RND.pdf)