Mark Towers's Projects
The Arcade Learning Environment (ALE) -- a platform for AI research.
A tool to automate installing Atari ROMs for the Arcade Learning Environment
Massively parallel rigidbody physics simulation on accelerator hardware.
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
A benchmark for offline reinforcement learning.
Research project on Resource-elastic tasks for edge cloud computing
A toolkit for developing and comparing reinforcement learning algorithms.
Code for Gym documentation website
MiniWorld: Minimalistic 3D Environment for RL & Robotics Research
A standard API for reinforcement learning and a diverse set of reference environments (formerly Gym)
A conda-smithy repository for gymnasium.
A minimalist environment for decision-making in autonomous driving
A maintained fork of the MAgent Multi-Agent RL Library
An open source robotics benchmark for meta- and multi-task reinforcement learning
A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities
Minimalistic gridworld package for OpenAI Gym
MiniWoB++: a web interaction benchmark for reinforcement learning
Multi-objective Gymnasium environments for reinforcement learning
Flexible resource allocation for edge cloud computing with reinforcement learning
Gym for multi-agent reinforcement learning
Procgen2: A community maintained fork of procgen
Static type checker for Python
A collection of pre-trained RL agents using Stable Baselines3
An API conversion tool for popular external reinforcement learning environments
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.