Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.

⚡ ⚡ 𝘋𝘦𝘦𝘱 𝘙𝘓 𝘈𝘭𝘨𝘰𝘵𝘳𝘢𝘥𝘪𝘯𝘨 𝘸𝘪𝘵𝘩 𝘙𝘢𝘺 𝘈𝘗𝘐

A custom MARL (multi-agent reinforcement learning) environment where multiple agents trade against one another (self-play) in a zero-sum continuous double auction. Ray [RLlib] is used for training.

An open, minimalist Gymnasium environment for autonomous coordination in wireless mobile networks.

Deep Reinforcement Learning For Trading

An introductory tutorial about leveraging Ray core features for distributed patterns.

Walkthroughs for DSL, AirSim, the Vector Institute, and more

RLlib tutorials

Adaptive real-time traffic light signal control system using Deep Multi-Agent Reinforcement Learning

Dynamic multi-cell selection for cooperative multipoint (CoMP) using (multi-agent) deep reinforcement learning

Reinforcement learning algorithms in RLlib

An example implementation of an OpenAI Gym environment used for a Ray RLlib tutorial

An open source library for connecting AnyLogic models with Reinforcement Learning frameworks through OpenAI Gymnasium

Super Mario Bros training with Ray RLlib DQN algorithm

Used Flow, Ray/RLlib and OpenAI Gym to simulate and train autonomous vehicles/human drivers in SUMO (Simulation of Urban Mobility)

RL environment replicating the werewolf game to study emergent communication

Tutorial for Ray

A Predator-Prey-Grass multi-agent gridworld environment implemented with Farama's Gymnasium and PettingZoo. Featuring dynamic spawning and deletion and partial observability of agents.