Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with Gymnasium, PettingZoo, and popular RL libraries.

Projects from basic algorithms to MARL. Implements MADDPG,MATD3,MA/HAPPO in Predator-Prey pursuit games with PettingZoo MPE environments.

PyTorch implements multi-agent reinforcement learning algorithms, including QMIX, Independent PPO, Centralized PPO, Grid Wise Control, Grid Wise Control+PPO, Grid Wise Control+DDPG.

A gym environment for a miniature racecar using the pybullet physics engine.

implementation of MADDPG using PettingZoo and PyTorch

Jax and Torch Multi-Agent SAC on PettingZoo API

Training of Drone Swarms using StableBaselines3, PettingZoo, AirSim and UE4

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.

SocialGym 2: A lightweight benchmark and simulator for multi-robot social navigation using ROS and the OpenAI gym.

A custom reinforcement learning environment for OpenAI Gym & PettingZoo that implements various Stag Hunt-like social dilemma games.

A modern implementation of MADDPG and MADDPG-Approx algorithms using PyTorch and PettingZoo environments. This project provides a clean, modular framework for multi-agent reinforcement learning research, featuring parallel training capabilities, comprehensive visualization tools, and support for various cooperative and competitive scenarios

Multi-Agent Reinforcement Learning Environment for the card game SkyJo, compatible with PettingZoo and RLLIB

Unity and Python Reinforcement and Imitation Learning with Gymnasium and PettingZoo API.

Training of Drone Swarms using StableBaselines3, PettingZoo, AirSim and UE4

Extended, multi-agent, and multi-objective (MaMoRL / MoMaRL) gridworld environments building framework based on DeepMind's AI Safety Gridworlds. This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. It is made compatible with OpenAI's Gym/Gymnasium and Farama Foundation PettingZoo.

Interactive Multi-Agent Reinforcement Learning Environment for the board game Gobblet using PettingZoo.

🕹 Pikachu-volleyball game-based multi-agent RL environment using PettingZoo

Multi-agent RL algorithm

The Multi-Agent RLRM (Reinforcement Learning with Reward Machines) Framework is a library designed to facilitate the formulation of multi-agent problems and solve them through reinforcement learning. The framework supports the integration of Reward Machines (RMs), providing a modular and flexible structure for defining complex tasks.

A PettingZoo AECEnv implementation of the board game Fanorona