Know an awesome toolkit in reinforcement learning? Tell us through the chat button on bottom right!

BYU Holodeck

Brigham Young University

Holodeck is a simulator based on the Unreal Engine that can be used for research, classes, or fun. It consists of agents (including humanoid robots and UAVs), environments (such as cities, forests, and deserts), Linux and Windows support, and a set of python bindings that make programmatic interaction easy. Plus, it can be run headlessly and/or containerized for massively parallel deep reinforcement learning research.



ChainerRL is a deep reinforcement learning library that implements various state-of-the-art deep reinforcement algorithms in Python using Chainer, a flexible deep learning framework.


Intel Nervana

Coach is a python reinforcement learning framework containing implementation of many state-of-the-art algorithms. It exposes a set of easy-to-use APIs for experimenting with new RL algorithms, and allows simple integration of new environments to solve. Basic RL components (algorithms, environments, neural network architectures, exploration policies, ...) are well decoupled, so that extending and reusing existing components is fairly painless.

DeepMind Control Suite and Package


The DeepMind Control Suite is a set of continuous control tasks with a standardised structure and interpretable rewards, intended to serve as performance benchmarks for reinforcement learning agents. The tasks are written in Python and powered by the MuJoCo physics engine, making them easy to use and modify.

DeepMind Lab


DeepMind Lab is a 3D learning environment based on id Software's Quake III Arena via ioquake3 and other open source software. DeepMind Lab provides a suite of challenging 3D navigation and puzzle-solving tasks for learning agents. Its primary purpose is to act as a testbed for research in artificial intelligence, especially deep reinforcement learning.



Dopamine is a research framework for fast prototyping of reinforcement learning algorithms. It aims to fill the need for a small, easily grokked codebase in which users can freely experiment with wild ideas (speculative research).



ELF is an Extensive, Lightweight, and Flexible platform for game research. We have used it to build our Go playing bot, ELF OpenGo, which achieved a 14-0 record versus four global top-30 players in April 2018. The final score is 20-0 (each professional Go players play 5 games).



Garage is a framework for developing and evaluating reinforcement learning algorithms. It includes a wide range of continuous control tasks plus implementations of algorithms. Garage is fully compatible with OpenAI Gym. All garage environments implement gym.Env, so all garage components can also be used with any environment implementing gym.Env.

General Video Game AI Competition

The GVG-AI Competition explores the problem of creating controllers for general video game playing. How would you create a single agent that is able to play any game it is given? Could you program an agent that is able to play a wide variety of games, without knowing which games are to be played? Can you create an automatic level generation that designs levels for any game is given?



You shouldn't play video games all day, so shouldn't your AI! Gibson is a virtual environment based off of real-world, as opposed to games or artificial environments, to support learning perception. Gibson enables developing algorithms that explore both perception and action hand in hand.