Reinforcement Learning Examples

Pong environment

Policy Gradients
Checkpoint weights

Lunar Lander environment

Deep Q-Network
Checkpoint weights

Policy Gradients
Checkpoint weights

Cartpole environment

Policy Gradients
Checkpoint weights

Deep Q-Network
Checkpoint weights

Mario environment

Policy Gradients
Checkpoint weights

Plot of average reward per 10 episodes

Double Deep Q-Network
Checkpoint weights

Plot of average reward per 10 episodes

PPO+GAE
Checkpoint weights

Plot of average reward per 10 episodes

Highway environments

Highway environnment

https://user-images.githubusercontent.com/8986329/123654361-ad2a5b80-d836-11eb-8b43-f1d949e93eca.mp4

Double Deep Q-Network
Checkpoint weights

Merge environnment

https://user-images.githubusercontent.com/8986329/123638313-b5c76580-d827-11eb-9c3b-a757de345d43.mp4

Double Deep Q-Network
Checkpoint weights

Roundabout environnment

https://user-images.githubusercontent.com/8986329/123638588-0212a580-d828-11eb-9b70-397898209223.mp4

Double Deep Q-Network
Checkpoint weights

Intersection environnment

https://user-images.githubusercontent.com/8986329/123638705-24a4be80-d828-11eb-866b-4bfb0b8d1234.mp4

Double Deep Q-Network
Checkpoint weights

Parking environnment

https://user-images.githubusercontent.com/8986329/123638469-e3acaa00-d827-11eb-92db-194c340d3ba4.mp4

PPO+GAE
Checkpoint weights

Racetrack environnment

https://user-images.githubusercontent.com/8986329/141271898-b30fa0d2-7a78-4ff4-9b0f-8cf996936473.mp4

PPO+GAE
Checkpoint weights

PyBullet Walker2D environment

https://user-images.githubusercontent.com/8986329/123640398-cb3d8f00-d829-11eb-8619-0688a4035ff7.mp4

PPO+GAE
Checkpoint weights

Plot of average reward per 50 episodes