Skip to content

Tutorial:

Installation
Quick Start
Further Usage
Custom Environments
- Single-Agent
- Multi-Agent
Custom Algorithms
- DRL
- MARL
Custom Callback

Algorithms:

Single-Agent RL
- DQN
- Double DQN
- Dueling DQN
- Noisy DQN
- PER DQN
- C51
- QR-DQN
- DRQN
- PG
- NPG
- A2C
- PPO
- PPO-KL
- PPG
- SAC
- DDPG
- TD3
- P-DQN
- MP-DQN
- SP-DQN
Multi-Agent RL
- IQL
- VDN
- QMIX
- WQMIX
- QTRAN
- DCG
- IDDPG
- MADDPG
- IAC
- COMA
- VDAC
- IPPO
- MAPPO
- MFQ
- MFAC
- ISAC
- MASAC
- MATD3
- IC3Net
Model-based RL
Constructive RL
- CURL
- SPR
- DrQ
Offline RL
- TD3BC

Benchmarks:

Start Benchmark
Benchmark Results
- MuJoCo
- Atari
- SMAC
Add New Benchmark

APIs:

common
configs
engine
environments
- single_agent_env
- multi_agent_env
  - MPE
  - RWARE
  - SMAC
  - Football
  - Drones
  - Magent2
- vectorization
- utils
  - Base Class
  - Wrappers
torch
tensorflow
mindspore

Development:

Github
Release Log
Contribute to XuanCe
Contribute to Docs (EN)
Contribute to Docs (CN)

utils¶

device¶

distributions¶

harmonizer¶

layers¶

layers4dreamer¶

operations¶

value_norm¶

representations

Copyright © 2023, XuanCe Contributors.

Made with Sphinx and @pradyunsg's Furo

On this page

utils