open_spiel
Game RL framework
A framework for researching and developing reinforcement learning algorithms in game environments.
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
4k stars
106 watching
939 forks
Language: C++
last commit: 3 months ago cppgamesmultiagentpythonreinforcement-learning
Related projects:
| Repository | Description | Stars |
|---|---|---|
 openai/neural-mmo | A framework for creating agents that can scale to the complexity of the real world by simulating a massively multiagent game environment | 1,594 |
 packtpublishing/hands-on-intelligent-agents-with-openai-gym | Teaching software developers to build intelligent agents using deep reinforcement learning and OpenAI Gym | 374 |
| google-deepmind/lab | A 3D environment for testing and training artificial intelligence agents | 7,146 |
 securitygames/oef | Provides tools and algorithms for developing reinforcement learning policies in game environments. | 3 |
 farama-foundation/gymnasium | Develops and compares reinforcement learning algorithms by providing a standard API to communicate between learning algorithms and environments | 7,613 |
 tju-drl-lab/ai-optimizer | A next-generation deep reinforcement learning toolkit with libraries for multiagent, self-supervised, offline, and transfer/reinforcement learning | 4,848 |
| google-deepmind/spriteworld | An environment designed to test and train reinforcement learning algorithms in a flexible, procedurally generated 2D space with various objects and interactions. | 369 |
 isl-org/open3d | A C++ library for rapid development of software that processes 3D data | 11,648 |
| google-deepmind/dm_control | A software stack for simulating physics-based environments and training reinforcement learning agents | 3,849 |
| openai/baselines | High-quality implementations of reinforcement learning algorithms for research and development purposes | 15,885 |
 rdiankov/openrave | An environment for testing and developing motion planning algorithms for robotics | 731 |
| google-deepmind/acme | A toolkit for building and deploying reinforcement learning agents | 3,542 |
 unity-technologies/ml-agents | Enables game developers to train intelligent agents using reinforcement learning and imitation learning. | 17,334 |
| openai/procgen | A benchmark for evaluating reinforcement learning agent performance on procedurally generated game-like environments. | 1,030 |
 open-mmlab/mmengine | Provides a flexible and configurable framework for training deep learning models with PyTorch. | 1,196 |