rllib

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.

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

⚡ ⚡ 𝘋𝘦𝘦𝘱 𝘙𝘓 𝘈𝘭𝘨𝘰𝘵𝘳𝘢𝘥𝘪𝘯𝘨 𝘸𝘪𝘵𝘩 𝘙𝘢𝘺 𝘈𝘗𝘐

The MARL extension for RLlib. A benchmark for research and industry.

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.

Reinforcement learning algorithms in RLlib

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.

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

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)

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

AI Economist Training Examples

JupyterLab Notebook for Mesosphere DC/OS

RL environment replicating the werewolf game to study emergent communication