OpenSpiel: A Framework for Reinforcement Learning in Games

DeepMind's open-source library of 70+ board, card, matrix, and partial-info games with a uniform API for RL, search, and game-theory research.

Open

Publisher: Google DeepMind
Year: 2019
Venue: preprint
ArXiv: arxiv.org/abs/1908.09453
Code: github.com/google-deepmind/open_spiel
Authors: 27
Hosting: External sourcelicense unknown

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text: arxiv.org/abs/1908.09453
TL;DR: semanticscholar.org/paper/232bd009964a9bbf4757227aae94d1a139350e04
Code: github.com/google-deepmind/open_spiel

Attribution policy →

Introduces 2 artifacts - 2 tools

TL;DR

Semantic Scholar

This document serves both as an overview of the code base and an introduction to the terminology, core concepts, and algorithms across the fields of reinforcement learning, computational game theory, and search.

Artifacts

Tools

Openspiel Env OpenSpiel