Repository files navigation

OpenSpiel is a collection of environments and algorithms for research in generalreinforcement learning and search/planning in games. OpenSpiel supports n-player(single- and multi- agent) zero-sum, cooperative and general-sum, one-shot andsequential, strictly turn-taking and simultaneous-move, perfect and imperfectinformation games, as well as traditional multiagent environments such as(partially- and fully- observable) grid worlds and social dilemmas. OpenSpielalso includes tools to analyze learning dynamics and other common evaluationmetrics. Games are represented as procedural extensive-form games, with somenatural extensions. The core API and games are implemented in C++ and exposed toPython. Algorithms and tools are written both in C++ and Python.

To try OpenSpiel in Google Colaboratory, please refer toopen_spiel/colabs subdirectory or starthere.

Please choose among the following options:

• Installing OpenSpiel
• Introduction to OpenSpiel
• API Overview and First Example
• API Reference
• Overview of Implemented Games
• Overview of Implemented Algorithms
• Developer Guide
• Using OpenSpiel as a C++ Library
• Guidelines and Contributing
• Authors

For a longer introduction to the core concepts, formalisms, and terminology,including an overview of the algorithms and some results, please seeOpenSpiel: A Framework for Reinforcement Learning in Games.

For an overview of OpenSpiel and example uses of the core API, please check outour tutorials:

• Motivation, Core API, Brief Intro to Replictor Dynamics and ImperfectInformation Games by MarcLanctot.(slides)(colab)
• Motivation, Core API, Implementing CFR and REINFORCE on Kuhn poker, Leducpoker, and Goofspiel by EdwardLockhart.(slides)(colab)

If you use OpenSpiel in your research, please cite the paper using the followingBibTeX:

@article{LanctotEtAl2019OpenSpiel,title     ={{OpenSpiel}: A Framework for Reinforcement Learning in Games},author    ={Marc Lanctot and Edward Lockhart and Jean-Baptiste Lespiau and               Vinicius Zambaldi and Satyaki Upadhyay and Julien P\'{e}rolat and               Sriram Srinivasan and Finbarr Timbers and Karl Tuyls and               Shayegan Omidshafiei and Daniel Hennes and Dustin Morrill and               Paul Muller and Timo Ewalds and Ryan Faulkner and J\'{a}nos Kram\'{a}r               and Bart De Vylder and Brennan Saeta and James Bradbury and David Ding               and Sebastian Borgeaud and Matthew Lai and Julian Schrittwieser and               Thomas Anthony and Edward Hughes and Ivo Danihelka and Jonah Ryan-Davis},year      ={2019},eprint    ={1908.09453},archivePrefix ={arXiv},primaryClass ={cs.LG},journal   ={CoRR},volume    ={abs/1908.09453},url       ={http://arxiv.org/abs/1908.09453},}

We useSemantic Versioning.