The Rational-Macro Agent Based Model. A Python (multi-agent) reinforcement learning interface of the "CATS" model.

A Predator-Prey-Grass multi-objective multi-agent gridworld environment implemented with Farama's Gymnasium, PettingZoo and MOMAland, featuring dynamic agent spawning and deletion, where agents have partial observability.

Mujoco Ant control with Reinforcement Learning / MARL

Source code for the paper "Toward Finding Strong Pareto Optimal Policies in Multi-Agent Reinforcement Learning"

An experimental Snake game where a Deep Q-Network (DQN) agent learns to navigate the environment, avoid obstacles, and find food using reinforcement learning techniques.

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

Repo associated with the paper: Algorithmic Collusion And The Minimum Price Markov Game

Auto-Multilift is a novel learning framework for cooperative load transportation with quadrotors. It can automatically tune various MPC hyperparameters, which are modeled by DNNs and difficult to tune manually, via reinforcement learning in a distributed and closed-loop manner.

OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

This is a framework for the research on multi-agent reinforcement learning and the implementation of the experiments in the paper titled by ''Shapley Q-value: A Local Reward Approach to Solve Global Reward Games''.

A suite of test scenarios for multi-agent reinforcement learning.

IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning

Algorithms to solve the DSSE environment, focusing on optimizing drone swarm search and navigation for critical applications.

This repository presents a multi-agent reinforcement learning approach for energy-efficient collaborative control of base stations in 5G networks.

Paper list of multi-agent reinforcement learning (MARL)

The Drone Swarm Search project provides an environment for SAR missions built on PettingZoo, where agents, represented by drones, are tasked with locating targets identified as shipwrecked individuals.

Multi-Agent Reinforcement Learning project

CMSC818B Mini-Project #1: Multi-Agent Algorithms

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

This is the official site for the paper POMA published in Advanced Intelligent Systems.