Check out the new game server:

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

BabyAI platform. A testbed for training agents to understand and execute language commands.

Build RL environments for LLM training

ns3-gym - The Playground for Reinforcement Learning in Networking Research

High Fidelity Simulator for Reinforcement Learning and Robotics Research.

IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks

A simple, easy, customizable Gymnasium environment for trading.

An open source toolkit for Distributed Deep Reinforcement Learning on real and simulated robots.

Grid2Op a testbed platform to model sequential decision making in power systems.

This repository is for an open-source environment for multi-agent active voltage control on power distribution networks (MAPDN).

OSS RL environment + evals toolkit

K-Sim Gym: Making robots useful with RL. Built on top of K-Sim.

A car soccer environment inspired by Rocket League for deep reinforcement learning experiments in an adversarial self-play setting.

Deep Reinforcement Learning in C#

Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)

EvoRL is a fully GPU-accelerated framework for Evolutionary Reinforcement Learning, implemented with JAX. It supports Reinforcement Learning (RL), Evolutionary Computation (EC), Evolution-guided Reinforcement Learning (ERL), AutoRL, and seamless integration with GPU-optimized simulation environments.

An OpenAi Gym environment for the Job Shop Scheduling problem.

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

Repository of implementations of classic and sota rl algorithms from scratch in PyTorch

FurnitureBench: Real-World Furniture Assembly Benchmark (RSS 2023)

UAV Flight Simulator for Reinforcement Learning Research

Gym environment for building simulation and control using reinforcement learning

This repo contains a curative list of robot learning (mainly for manipulation) resources.

TensorTrade-NG is an open source Python framework for building, training, evaluating, and deploying robust trading algorithms using reinforcement learning.

Robotic simulation in Unity with ROS integration.

A unified end-to-end learning and control framework that is able to learn a (neural) control objective function, dynamics equation, control policy, or/and optimal trajectory in a control system.

An easy-to-use reinforcement learning library for research and education.

Assetto Corsa OpenAI Gym Environment

Isaaclab-based grasp learning test bench