The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)

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

Multi-Agent Connected Autonomous Driving (MACAD) Gym environments for Deep RL. Code for the paper presented in the Machine Learning for Autonomous Driving Workshop at NeurIPS 2019:

Multi-objective Gymnasium environments for reinforcement learning

PyTorch implementation of Hierarchical Actor Critic (HAC) for OpenAI gym environments

Collection of Reinforcement Learning / Meta Reinforcement Learning Environments.

Partially Observable Process Gym

A framework to design Reinforcement Learning environments that model Active Network Management (ANM) tasks in electricity distribution networks.

A power network simulator with a Reinforcement Learning-focused usage.

Gym environments and agents for autonomous driving.

A toolkit for auto-generation of OpenAI Gym environments from RDDL description files.

A collection of Gymnasium compatible games for reinforcement learning.

Pytorch Implementation of Stochastic MuZero for gym environment. This algorithm is capable of supporting a wide range of action and observation spaces, including both discrete and continuous variations.

An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.

Set of reinforcement learning environments for optical networks

🎳 Environments for Reinforcement Learning

Framework for integrating ROS and Gazebo with gymnasium, streamlining the development and training of RL algorithms in realistic robot simulations.

Cellular Automata Environments for Reinforcement Learning

A collection of RL gymnasium environments for learning to grasp 3D deformable objects.

Reinforcement learning in haskell

Repository of implementation of few algorithms for Underactuated Systems in Robotics and solutions to some interesting problems

Pytorch Implementation of MuZero Unplugged for gym environment. This algorithm is capable of supporting a wide range of action and observation spaces, including both discrete and continuous variations.

Implementations of a large collection of reinforcement learning algorithms.

Gym Interface Wrapper for Simulink Models

A reinforcement learning-oriented Panda Emika Franka gazebo simulation.

Pytorch Implementation of MuZero for gym environment. It support any Discrete , Box and Box2D configuration for the action space and observation space.

Beer Game implemented as an OpenAI gym environment.

A toolkit for working with RDDL domains in Python3.

Multi agent gym environment based on the classic Snake game with implementations of various reinforcement learning algorithms in pytorch

中国象棋gym环境