# RL_Algorithms

**Repository Path**: uvCut/RL_Algorithms

## Basic Information

- **Project Name**: RL_Algorithms
- **Description**: 强化学习经典算法复现
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-02-21
- **Last Updated**: 2025-02-21

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# RL_Algorithms
Practice of some basic algorithms of reinforcement learning
- [x] Model Based Environment
- [x] Dynamic Programming(Value \ Policy Iteration)
- [x] Monte Carlo Basic(MC Basic \ MC Exploring Starts \ MC Epsilon-Greedy)
- [x] Temporal Difference(Sarsa \ Expected Sarsa \ Q-Learning On-Policy \ Q-Learning Off-Policy)
- [x] DQN(Deep Q Network)
- [x] Policy Gradient(REINFORCE)
- [x] A2C(Advantage Actor-Critic)
- [x] PPO(Proximal Policy Optimization)
- [x] DDPG(Deep Deterministic Policy Gradient)
- [x] TD3(Twin Delayed Deep Deterministic Policy Gradient Algorithm)
- [x] SAC(Soft Actor Critic)
- [ ] IPPO(Independent Proximal Policy Optimization)
- [ ] VDN(Value-Decomposition Networks)
- [ ] QMIX(Monotonic Value Function Factorisation)
- [ ] MADDPG(Multi-Agent Deep Deterministic Policy Gradient)
- [ ] MAPPO(Multi-Agent Proximal Policy Optimization)

## Code practices for the MathFoundationRL project
### Basic algorithm theory learning
https://github.com/MathFoundationRL/Book-Mathematical-Foundation-of-Reinforcement-Learning
### Basic algorithm theory learning notes
https://blog.csdn.net/qq_42828479/category_12665114.html?spm=1001.2014.3001.5482
### Basic algorithm practice
https://blog.csdn.net/qq_42828479/category_12774316.html?spm=1001.2014.3001.5482
### Reference Projects
https://github.com/boyu-ai/Hands-on-RL
https://github.com/datawhalechina/easy-rl
https://github.com/jwk1rose/RL_Learning
### Prof. Shiyu Zhao YYDS