easy-rl/codes

Eng|中文

Introduction

This repo is used to learn basic RL algorithms, we will make it detailed comment and clear structure as much as possible:

The code structure mainly contains several scripts as following：

• model.py basic network model of RL, like MLP, CNN
• memory.py Replay Buffer
• plot.py use seaborn to plot rewards curve，saved in folder result.
• env.py to custom or normalize environments
• agent.py core algorithms, include a python Class with functions(choose action, update)
• main.py main function

Note that model.py,memory.py,plot.py shall be utilized in different algorithms，thus they are put into common folder。

Runnig Environment

python 3.7.9、pytorch 1.6.0、gym 0.18.0

Usage

run main.py or main.ipynb

Schedule

Name	Related materials	Used Envs	Notes
On-Policy First-Visit MC		Racetrack
Q-Learning		CliffWalking-v0
Sarsa		Racetrack
DQN	DQN-paper	CartPole-v0
DQN-cnn	DQN-paper	CartPole-v0
DoubleDQN		CartPole-v0	not well
Hierarchical DQN	Hierarchical DQN	CartPole-v0
PolicyGradient		CartPole-v0
A2C		CartPole-v0
A3C
SAC
PPO	PPO paper	CartPole-v0
DDPG	DDPG Paper	Pendulum-v0
TD3	Twin Dueling DDPG Paper
GAIL

Refs

RL-Adventure-2

RL-Adventure

https://www.cnblogs.com/lucifer1997/p/13458563.html