Python
RLlibray-project/ray
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.
Deep learningRL
44.1k updated today
DI-engine
opendilab/DI-engine
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.
- reinforcement-learning
- multiagent-reinforcement-learning
- self-play
- imitation-learning
- inverse-reinforcement-learning
- exploration-exploitation
- distributed-system
- python
More in Python
ML-From-Scratcheriklindernoren/ML-From-Scratch
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.
GeneralDeep learningRL
33.1k updated 3y ago
GymnasiumFarama-Foundation/Gymnasium
A library for developing and comparing reinforcement learning algorithms (successor of [gym])(https://github.com/openai/gym).
RL
12.7k updated today
Spinning Upopenai/spinningup
An educational resource designed to let anyone learn to become a skilled practitioner in deep reinforcement learning
RL
12k updated 2y ago
DeepMind Labdeepmind/lab
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.
Deep learningRL
7.4k updated 3y ago
Serpent.AISerpentAI/SerpentAI Archived
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.
Deep learningVisionRL
7k archived
acmegoogle-deepmind/acme
An Open Source Distributed Framework for Reinforcement Learning that makes build and train your agents easily.
RL
4.1k updated 1d ago
3.6k archived