Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.

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

⚡ ⚡ 𝘋𝘦𝘦𝘱 𝘙𝘓 𝘈𝘭𝘨𝘰𝘵𝘳𝘢𝘥𝘪𝘯𝘨 𝘸𝘪𝘵𝘩 𝘙𝘢𝘺 𝘈𝘗𝘐

VMAS is a vectorized framework 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.

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.

Deep Reinforcement Learning For Trading

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

RLlib tutorials

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

Reinforcement learning algorithms in RLlib

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

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

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

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

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

AI Economist Training Examples

JupyterLab Notebook for Mesosphere DC/OS

Training in bursts for defending against adversarial policies