Welcome to DI-engine’s documentation!

中文文档

User Guide

• Introduction
  • What is DI-engine?
  • Key Concepts
• Quickstart
  • Installation Guide
  • Hello World for DI
  • First Reinforcement Learning Program
  • More Reinforcement Learning Program (Customized Env)
• RL Algorithm Taxonomy
  • Model-Based Reinforcement Learning
  • Imitation Learning
  • Exploration Mechanisms in Reinforcement Learning
  • Multi-Agent Reinforcement Learning
  • Offline Reinforcement Learning
  • Safe Reinforcement Learning
  • Distributed Reinforcement Learning
  • Zero-sum Game
• System Design
  • Middleware
  • Distributed
  • Configuration File System
  • Agent
• Best Practice
  • How to migrate your own environment to DI-engine
  • How to customize the neural network model
  • How to construct environments easily with Env Wrapper
  • Buffer User Guide
  • How to construct a data pipeline for Imitation Learning / Offline Training
  • Random Seed
• API Doc
  • ding.agent
  • ding.config
  • ding.envs
  • ding.model
  • ding.policy
  • ding.rl_utils
  • ding.torch_utils
  • ding.utils
  • Framework
  • Data
  • Learner
  • Collector
  • Replay Buffer
  • Reward Model
  • League
• FAQ
  • Frequently Asked Questions

Reinforcement Learning Tutorial

• Introduction to RL
  • Basic Concepts
• Learn From DI-zoo
  • What is DI-zoo
  • The structure of DI-zoo
  • How to use DI-zoo
  • Customization of DI-zoo
  • List of algorithms and environments supported by DI-zoo
• RL Algorithms Cheat Sheet
  • 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 (DecisionTransformer)
  • QGPO
  • Diffuser (Plan Diffuser)
  • R2D2
  • GTrXL
  • QMIX
  • COMA
  • WQMIX
  • QTRAN
  • CollaQ
  • ATOC
  • MBPO
  • VPN
  • PLR
• RL Env Examples
  • 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

Developer Specification

• Specification
  • Middleware specification
  • Event Naming Convention
  • Specifications of DI-engine Config
• Code Style Guide
  • Basic Code Style Rules
  • yapf
  • flake8
  • Reasonable Import Order
• Unit Test Guide
  • Significance of Unit Testing
  • Types of Unit Test
  • How to Build Unit Test
  • How do Run Unit Test
• Diagrams and Visualization
  • PlantUML
  • graphviz
  • draw.io
  • snakeviz
• Github Cooperation
  • Git Usage
  • Github Usage