[NeurIPS 2025] VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

Implementations of IQL, QMIX, VDN, COMA, QTRAN, MAVEN, CommNet, DyMA-CL, and G2ANet on SMAC, the decentralised micromanagement scenario of StarCraft II

Learning Individual Intrinsic Reward in MARL

SMAC: The StarCraft Multi-Agent Challenge

Instrumented Principal Components Analysis

PCAtools: everything Principal Components Analysis

Codes of SeCA accompanying the paper "Sequential Cooperative Multi-Agent Reinforcement Learning"(AAMAS 2023). SeCA is a sequential credit assignment method that factorizes and simplifies the comple…

[NeurIPS 2020] PyTorch implementation of "Learning Implicit Credit Assignment for Cooperative Muti-Agent Reinforcement Learning"

Python Multi-Agent Reinforcement Learning framework

Code for our paper: Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library

An elegant PyTorch deep reinforcement learning library.

ELIGN: Expectation Alignment as a Multi-agent Intrinsic Reward

An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities

Common used path planning algorithms with animations.

A Modular and Multi-Modal Mapping Framework

Framework for Autonomous Navigation of Micro Aerial Vehicles

Space-Filling Forest* for milti-goal path planning

An Efficient Framework for Fast UAV Exploration

Transplant a implementation of MADDPG to the environment provided by openAI (multiagent-particle-envs).

Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging simulated continuous control single agent tasks. These methods have further been extended to mu…

Codes accompanying the paper "Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning" (NeurIPS 2021 Spotlight https://arxiv.org/abs/2106.03400)

Code for implementing/applying ODM*, PPO, MAAC, IC3Net and PRIMAL (PPO version) on a Multi-Agent gridworld environment.

Design a very first algorithm to compute the mixed strategy Nash equilibrium of games with continuous action space.

Une implémentation de l'algorithme de Nash mixte pour 3 joueurs avec 2 stratégies en Python.

[ICLR 2023] Come & try Decision-Intelligence version of "Agar"! Gobigger could also help you with multi-agent decision intelligence study.