multi-agent

Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.

A Platform for Many-agent Reinforcement Learning

Foundation is a flexible, modular, and composable framework to model socio-economic behaviors and dynamics with both agents and governments. This framework can be used in conjunction with reinforcement learning to learn optimal economic policies, as done by the AI Economist (https://www.einstein.ai/the-ai-economist).

Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.

PyBullet Gym environments for single and multi-agent reinforcement learning of quadcopter control

Awesome Game AI materials of Multi-Agent Reinforcement Learning

A collection of multi agent environments based on OpenAI gym.

PyTorch implementations of various Deep Reinforcement Learning (DRL) algorithms for both single agent and multi-agent.

This is the official implementation of Multi-Agent PPO (MAPPO).

Trajectory Planner in Multi-Agent and Dynamic Environments

The multi-agent version of TORCS for developing control algorithms for fully autonomous driving in the cluttered, multi-agent settings of everyday life.

Multi-Agent Robotics Simulator

Block-style programming environment for multi agent system, based on MIT Scratch.

Open-Source Framework for Development, Simulation and Benchmarking of Behavior Planning Algorithms for Autonomous Driving

API to run VirtualHome, a Multi-Agent Household Simulator

TensorSwarm: A framework for reinforcement learning of robot swarms.

PGDrive: an open-ended driving simulator with infinite scenes from procedural generation

Lightweight multi-agent gridworld Gym environment

Multi & Single Agent Reinforcement Learning for Traffic Signal Control Problem

[ICCV21] Official implementation of the "Social NCE: Contrastive Learning of Socially-aware Motion Representations" in PyTorch.

Algorithm for prioritized multi-agent path finding (MAPF) in grid-worlds. Moves into arbitrary directions are allowed (each agent is allowed to follow any-angle path on the grid). Timeline is continuous, i.e. action durations are not explicitly discretized into timesteps. Different agents' size and moving speed are supported. Planning is carried out in (x, y, \theta) configuration space, i.e. agents' orientation are taken into account.

A Universal Deep Reinforcement Learning Framework

Mobile Agent that moves on a platform distributed on many machines and recover the mac address of each machine during the deplacement

Continuous CBS - a modification of conflict based search algorithm, that allows to perform actions (move, wait) of arbitrary duration. Timeline is not discretized, i.e. is continuous.

MultiAgent Development Kit - version 5

This is an implementation of the paper "Coordinated Multi Agent Imitation Learning", or the Sloan version "Data-Driven Ghosting using Deep Imitation Learning" using Tensorflow

Collection of Deep Reinforcement Learning Algorithms implemented in PyTorch.

reproduce some RL or Multi-Agent models