31 libraries, 17 updated this year
Libraries for agents that learn by acting in an environment. Gymnasium, the Farama Foundation's maintained continuation of OpenAI Gym, defines the standard environment interface. Stable-Baselines3 implements reliable versions of common algorithms such as PPO, SAC and DQN in PyTorch, and RLlib scales training across a cluster on Ray.
31 libraries
RLlib is an industry level, highly scalable RL library for tf and torch, based on Ray. It's used by companies like Amazon and Microsoft to solve real-world decision making problems at scale.
PythonDeep learning
Implementations of Machine Learning models from scratch in Python with a focus on transparency. Aims to showcase the nuts and bolts of ML in an accessible way.
PythonGeneralDeep learning
PyTorch implementations of Stable Baselines (deep) reinforcement learning algorithms.
Go
A library for developing and comparing reinforcement learning algorithms (successor of [gym])(https://github.com/openai/gym).
PythonAn educational resource designed to let anyone learn to become a skilled practitioner in deep reinforcement learning
Python
Machine learning experiment tracking, dataset versioning, hyperparameter search, visualization, and collaboration
DeepMind Lab is a 3D learning environment based on id Software's Quake III Arena via ioquake3 and other open source software. Its primary purpose is to act as a testbed for research in artificial intelligence, especially deep reinforcement learning.
PythonDeep learning
Serpent.AI is a game agent framework that allows you to turn any video game you own into a sandbox to develop AI and machine learning experiments. For both researchers and hobbyists.
PythonDeep learningVision
An Open Source Distributed Framework for Reinforcement Learning that makes build and train your agents easily.
Python
A platform for reproducible and scalable machine learning and deep learning.
C++GeneralDeep learning
DI-engine is a generalized Decision Intelligence engine. It supports most basic deep reinforcement learning (DRL) algorithms, such as DQN, PPO, SAC, and domain-specific algorithms like QMIX in multi-agent RL, GAIL in inverse RL, and RND in exploration problems.
Python
Debugging and visualization tool for machine learning and data science. It extensively leverages Jupyter Notebook to show real-time visualizations of data in running processes such as machine learning training.
PythonDeep learningData & viz
High-level utils for PyTorch DL & RL research. It was developed with a focus on reproducibility, fast experimentation and code/ideas reusing. Being able to research/develop something new, rather than write another regular train loop.
PythonGeneralDeep learningVisionOpen-source software for robot simulation, integrated with OpenAI Gym.
Python
A toolkit for reproducible reinforcement learning research
PythonDeep learning
ViZDoom allows developing AI bots that play Doom using only the visual information (the screen buffer). It is primarily intended for research in machine visual learning, and deep reinforcement learning, in particular.
PythonDeep learningAn open source robotics benchmark for meta- and multi-task reinforcement learning
Python
The fastest deep reinforcement learning library for continuous control, implemented header-only in pure, dependency-free C++ (Python bindings available as well).
C++Deep learning
Reinforcement learning using Markov Decision Processes.
JavaScriptGeneral
Application-oriented deep reinforcement learning framework addressing real-world decision problems.
PythonDeep learning
A fast Evolution Strategy implementation in Python.
PythonGeneralDeep learning
Plug-and-play, parallel Go framework for NeuroEvolution of Augmenting Topologies (NEAT).
GoGeneralDeep learning
Gym4ReaL is a comprehensive suite of realistic environments designed to support the development and evaluation of RL algorithms that can operate in real-world scenarios. The suite includes a diverse set of tasks exposing RL algorithms to a variety of practical challenges.
Python
An educational, pure JavaScript library designed to help developers and students understand the inner workings of ML algorithms without the magic of external libraries.
JavaScriptGeneral
A VS Code extension to view Weights & Biases experiments, logs, and artifacts within the IDE, eliminating the need to switch to the web UI and keeping data private.
Reinforcement Learning Coach by Intel® AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
Python
