
open_spiel
by google-deepmind (organization)
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games. (description from the project’s GitHub page)
Repository facts
- Stars
- 5,539
- Forks
- 1,203
- Open issues and pull requests
- 86
- Primary language
- C++
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- google-deepmind · Organization
- Created
- Jul 22, 2019
- Last push
- Aug 31, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 8,946: sjtu-marl/malib
A parallel framework for population-based multi-agent reinforcement learning.
558 starsPythonMITLast push Dec 14, 2023
Rank 943: VowpalWabbit/vowpal_wabbit
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, a…
8,730 starsC++Other licenseLast push Oct 15, 2026
Rank 5,976: rl-tools/rl-tools
The Fastest Deep Reinforcement Learning Library
1,037 starsC++MITLast push Oct 18, 2026
Rank 7,859: utilForever/RosettaStone
Hearthstone simulator using C++ with some reinforcement learning
684 starsC++AGPL-3.0Last push Oct 18, 2026
Rank 6,360: instadeepai/Mava
🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX
938 starsPythonApache-2.0Last push Sep 9, 2026
Rank 1,881: BehaviorTree/BehaviorTree.CPP
Behavior Trees Library in C++. Batteries included.
4,250 starsC++MITLast push Oct 18, 2026