wassname/DeepRL

mirror of https://github.com/wassname/DeepRL.git synced 2026-08-22 11:40:47 +08:00

T

Shangtong Zhang d77cc46cbf Fix a bug of replay

2017-05-26 15:18:45 -06:00

.gitignore

Optimize replay buffer

2017-05-24 19:45:42 -06:00

async_agent.py

Pixel atari games with DQN

2017-05-20 22:09:18 -06:00

bootstrap.py

A3C

2017-05-13 13:48:18 -06:00

dqn_agent.py

Fix a bug of replay

2017-05-26 15:18:45 -06:00

LICENSE

Initial commit

2017-04-20 13:59:53 -06:00

main.py

Fix a bug of replay

2017-05-26 15:18:45 -06:00

network.py

Fix a bug of replay

2017-05-26 15:18:45 -06:00

policy.py

Pixel atari games with DQN

2017-05-20 22:09:18 -06:00

README.md

Pixel atari games with DQN

2017-05-20 22:09:18 -06:00

replay.py

Fix a bug of replay

2017-05-26 15:18:45 -06:00

task.py

Optimize replay buffer

2017-05-24 19:45:42 -06:00

README.md

DeepRL

Highly modularized implementation of popular deep RL algorithms powered by PyTorch

Deep Q-Learning
Asynchronous One-Step Q-Learning
Asynchronous One-Step Sarsa
Asynchronous N-Step Q-Learning
Asynchronous Advantage Actor Critic (A3C)

Tested with both classical control tasks (CartPole, LunarLander) and Atari games.

Try it out from main.py!