wassname/Deep-reinforcement-learning-with-pytorch: PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and .... - Deep-reinforcement-learning-with-pytorch - Gitea: Git with a cup of tea

wassname/Deep-reinforcement-learning-with-pytorch

0 Fork 0

mirror of https://github.com/wassname/Deep-reinforcement-learning-with-pytorch.git synced 2026-10-05 12:20:38 +08:00

T

Johnny He 7dcfbb3e5d Create PPO_pendulum.py

2018-11-05 20:55:03 +08:00

Create a2c_cartpole.py

2018-10-18 16:51:16 +08:00

Add files via upload

2018-10-10 16:17:53 +08:00

Add files via upload

2018-10-25 15:07:15 +08:00

Rename dqn/DQN.py to DQN/DQN.py

2018-10-31 21:19:03 +08:00

Rename dqn/DQN.py to DQN/DQN.py

2018-10-31 21:19:03 +08:00

Create README.md

2018-10-26 15:13:33 +08:00

policy gradient

Add files via upload

2018-10-08 10:02:12 +08:00

Create PPO_pendulum.py

2018-11-05 20:55:03 +08:00

Reinforcement learning application

Update README.md

2018-11-04 21:28:12 +08:00

Sparse reward tasks

Add files via upload

2018-10-30 14:29:16 +08:00

actor_critic_method.py

Create actor_critic_method.py

2018-07-10 11:47:42 +08:00

gridworld.py

Create gridworld.py

2018-07-10 11:47:11 +08:00

PolicyGradient.py

Create PolicyGradient.py

2018-08-07 10:54:21 +08:00

readme.md

Update readme.md

2018-10-31 11:29:56 +08:00

sarsa.py

add sarsa learning

2018-07-30 10:43:24 +08:00

td0.py

add q learning td0

2018-07-27 14:00:20 +08:00

readme.md

This repository will implement the classic deep reinforcement learning algorithms. The aim of this repository is to provide clear code for people to learn the deep reinforcement learning algorithm.

In the future, more algorithms will be added and the existing codes will also be maintained.

DQN

包含两个算法

Policy Gradient

使用下面的命令可以运行已经保存好的模型

python Run_Model.py

使用下面的命令开始训练

pytorch_MountainCar-v0.py

policyNet.pkl

这个是已经保存好的模型

Alphago zero

我将在兵棋游戏中复现alphago zero

欢迎关注中科院自动化所智能系统与工程中心

Actor-Critic