An open API service indexing awesome lists of open source software.

https://github.com/semitable/awesome-marl


https://github.com/semitable/awesome-marl

List: awesome-marl

Last synced: 4 months ago
JSON representation

Awesome Lists containing this project

README

          

# Awesome Multi-Agent Reinforcement Learning

A curated list of multi-agent reinforcement learning reading material, environments, and code implementations.

Maintainer(s): [Filippos Christianos](www.fchristianos.com)

# Contributing
Pull requests are always welcome!

# Table of Contents

- [Awesome Multi-Agent Reinforcement Learning](#awesome-multi-agent-reinforcement-learning)
- [Contributing](#contributing)
- [Table of Contents](#table-of-contents)
- [Theory & Reading Material](#theory--reading-material)
- [Papers](#papers)
- [Core (must read!)](#core-must-read)
- [Surveys](#surveys)
- [Cooperative MARL](#cooperative-marl)
- [Opponent Modelling](#opponent-modelling)
- [Other reading material (blogs, websites, videos)](#other-reading-material-blogs-websites-videos)
- [Environments](#environments)
- [Algorithm Implementations](#algorithm-implementations)

# Theory & Reading Material

## Papers
### Core (must read!)
### Surveys
### Cooperative MARL
### Opponent Modelling

## Other reading material (blogs, websites, videos)

# Environments

- [Level-based Foraging](https://github.com/semitable/lb-foraging) - mixed cooperative-competitive game, which focuses on the coordination of the agents involved.
- [Multi-Robot Warehouse](https://github.com/semitable/robotic-warehouse) - A simulated warehouse with robots moving and delivering requested goods.
- [StarCraft Multi-agent Challenge](https://github.com/oxwhirl/smac) - A decentralised micromanagement scenarios built on StarCraft II.
- [Multi-agent Particle Environment](https://github.com/openai/multiagent-particle-envs) - A diverse set of 2D tasks involving cooperation and competition between agents.
- [Malmö](https://github.com/microsoft/malmo) - An environment built on top of Minecraft. Also see [MarLÖ](https://github.com/crowdAI/marLo) (short for Multi-Agent Reinforcement Learning in MalmÖ).
- [Derk's Gym](https://gym.derkgame.com/) - A MOBA-style multi-agent competitive team-based game.
- [Flatland](https://flatland.aicrowd.com/) - Based on a real-world problem of coordinating a railway traffic infrastructure.
- [Neural-MMO](https://jsuarez5341.github.io/) - A massively multiagent game environment for training and evaluating intelligent agents.

# Algorithm Implementations
- [PyMARL](https://github.com/oxwhirl/pymarl) - WhiRL's framework for deep multi-agent reinforcement learning and includes implementations of QMIX, COMA, VDN, IQL, and QTRAN (only cooperative MARL).
- [Extended-PyMARL](https://github.com/uoe-agents/epymarl) - An extension of the above, with the addition of IA2C, IPPO, MADDPG, MAA2C and MAPPO. Also improves the consistency of the implementations for fair comparisons.