Table of Contents

Shortcuts

欢迎来到DI-engine的文档！¶

_images/head_image.png

用户指南

强化学习教程

强化学习简介
- 基本概念
从DI-zoo学习
RL算法速查表
- DQN
- C51
- QRDQN
- Rainbow
- IQN
- FQF
- SQL
- SQN
- MDQN
- Averaged-DQN
- A2C
- PPO
- ACER
- IMPALA
- PPG
- DDPG
- D4PG
- TD3
- SAC
- RND
- HER
- ICM
- DQfD
- SQIL
- GAIL
- TREX
- R2D3
- CQL
- TD3BC
- EDAC
- DT (决策变换器)
- QGPO
- Diffuser (计划扩散器)
- R2D2
- GTrXL
- QMIX
- COMA
- WQMIX
- QTRAN
- CollaQ
- ATOC
- MBPO
- VPN
- PLR
RL 环境示例
- Atari
- MuJoCo
- CartPole
- Pendulum
- BitFlip
- LunarLander
- BipedalWalker
- MiniGrid
- Slime Volleyball
- Procgen
- SMAC
- D4RL (MuJoCo)
- Google Research Football (Gfootball)
- Overcooked
- Bsuite
- PettingZoo
- dmc2gym
- Sokoban
- Gym-Super-Mario-Bros
- gym hybrid
- Evogym
- Metadrive
- Taxi