OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

A parallel framework for population-based multi-agent reinforcement learning.

The fastest way to bring multi-agent workflows to production.

A compilation of the best multi-agent papers

Code for ICLR 2019 paper: Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks

基于大语言模型(LLM)和多智能体(Multi-Agent)，探究AI写小说能力的边界

[ICRA2023] CoAlign: Robust Collaborative 3D Object Detection in Presence of Pose Errors

some Multiagent enviroment in 《Multi-agent Reinforcement Learning in Sequential Social Dilemmas》 and 《Value-Decomposition Networks For Cooperative Multi-Agent Learning》

CEO is an intuitive and modular AI agent framework for task automation.

A multi agent path planning solution under a warehouse scenario using Q learning and transfer learning.🤖️

Training code for GA3C-CADRL algorithm (collision avoidance with deep RL)

A framework to empower forecasting using Large Language Models (LLMs)

Code for the paper Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration

🛸 An implementation of multi-agent flocking formation control with specific formations that can follow a target without collision and can avoid obstacles.

✨🦋 illufly 是自我进化的 Agent 框架: 基于自我进化，快速创造价值

Based on David Silver's paper "Cooperative Pathfinding"

A collection of multi-agent reinforcement learning OpenAI gym environments

[CVPR2024] Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset

Pytorch implementation of Multi-Agent Generative Adversarial Imitation Learning