Reinforcement Learning Environments Python Packages

nemo-gym

Evaluate and improve models and agents using environments

hud-python

RL environments + evals for AI agents. Define once, train anything.

envpool

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

hud

RL environments + evals for AI agents. Define once, train anything.

agentenv-framework-protocol

Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now.

agentenv-framework

Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now.

nes-py

Native C++ NES emulator with Python/Gymnasium APIs, vector execution, and cross-platform packaging.

sinergym

Gym environment for building simulation and control using reinforcement learning

grid2op

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

riichienv

High-Performance Research Environment for Riichi Mahjong

esquilax

JAX Multi-Agent RL, Neuro-Evolution, and A-Life Library

pyflyt

UAV Flight Simulator for Reinforcement Learning Research

bourse

Rust Market Simulation Library with a Python API

verbs

Rust and Python Ethereum Agent Based Modelling Library

bark-ml

Gym environments and agents for autonomous driving.

dacbench

A benchmark library for Dynamic Algorithm Configuration.

pynds

PyNDS: A Python Wrapper for the Nintendo DS Emulator

gfootball

Check out the new game server:

target-gym

TargetGym: Fast Setpoint tracking environments in Jax.

gym-trading-env

A simple, easy, customizable Gymnasium environment for trading.

hrl-pybullet-envs

Locomotion HRL envs in pybullet

evorl-jax

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.

pcgym

Reinforcement learning environments for process control applications.

magbotsim

Magnetic Robotics simulation including reinforcement learning environments based on MuJoCo