multi-agent-learning 开源项目推荐（26 个）

AI4Finance-Foundation /FinRL

FinRL®：财务强化学习。🔥

LantaoYu /MARL-Papers

Paper list of multi-agent reinforcement learning (MARL)

proroklab /VectorizedMultiAgentSimulator

VMAS 是一个向量化可微模拟器，旨在高效进行多智能体强化学习基准测试。它由用 PyTorch 编写的向量化 2D 物理引擎和一组具有挑战性的多机器人场景组成。可通过简单模块化接口实现更多场景。

TimeBreaker /Multi-Agent-Reinforcement-Learning-papers

Multi-Agent Reinforcement Learning (MARL) papers

TimeBreaker /MARL-resources-collection

A Collection of Multi-Agent Reinforcement Learning (MARL) Resources

jiachenli94 /Awesome-Decision-Making-Reinforcement-Learning

A selection of state-of-the-art research materials on decision making and motion planning.

coperception /coperception

用于多智能体协作感知的SDK。

ai4ce /DiscoNet

[NeurIPS2021]学习多智能体感知的精炼协作图

zfw1226 /active_tracking_rl

Active visual tracking library based on PyTorch.

chuangyc /awesome-multiagent-learning

A curated list of multiagent learning and related area resources.

WeiChengTseng /awesome-multi-agent

A curated list of awesome multi-agent learning papers

cameronangliss /vgc-bench

An AI benchmark for Pokémon VGC with agent implementations using multi-agent reinforcement learning, behavior cloning, LLMs, and heuristics

roop-pal /Meta-Learning-for-StarCraft-II-Minigames

We reproduced DeepMind's results and implement a meta-learning (MLSH) agent which can generalize across minigames.

forrestlaine /TensorGames.jl

Computing mixed-strategy Nash Equilibria for games involving multiple players

nicehiro /catch-me-if-you-can

Multi agent reinforement learning. Chaser and runner.

abhijaysingh /pizzaro

Multi-agent collaboration using Reinforcement Learning

HowardLiYH /RISP

Regime-Invariant Specialist Pools (RISP): reward-independent specialist retention + episode-invariant decision-focused training for non-stationary markets. Theory, 11-arm experiments, three papers — honest nulls included. Companion to GAUSE.

Ayoub-etoullali /Activites-Pratiques-SMA-And-IA-Distribuee

Multiplayer Game, Security, DF Service Implementation, Genetic Algorithm Implementation, Multi-Agent Systems Enhanced With Q-Learning Implementation For Improved Decision-Making.

rahulkhunte /DAMN-prototype

Decentralized AI Memory Network (DAMN) — a persistent learning and memory-sharing infrastructure for autonomous agents. Blockchain + IPFS-based memory layer enabling cross-agent experience reuse and scalable distributed intelligence.

booo-wang /topology-aware-comm-compression

Practical multi-agent communication sandbox for topology-aware compression and result visualization.