Corpus ID: 201666696

OpenSpiel: A Framework for Reinforcement Learning in Games

  title={OpenSpiel: A Framework for Reinforcement Learning in Games},
  author={Marc Lanctot and Edward Lockhart and Jean-Baptiste Lespiau and V. Zambaldi and Satyaki Upadhyay and Julien P{\'e}rolat and Sriram Srinivasan and Finbarr Timbers and K. Tuyls and Shayegan Omidshafiei and D. Hennes and Dustin Morrill and P. Muller and Timo Ewalds and R. Faulkner and J{\'a}nos Kram{\'a}r and Bart De Vylder and Brennan Saeta and J. Bradbury and David Ding and Sebastian Borgeaud and Matthew Lai and Julian Schrittwieser and T. Anthony and Edward Hughes and Ivo Danihelka and Jonah Ryan-Davis},
  • Marc Lanctot, Edward Lockhart, +24 authors Jonah Ryan-Davis
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games. OpenSpiel supports n-player (single- and multi- agent) zero-sum, cooperative and general-sum, one-shot and sequential, strictly turn-taking and simultaneous-move, perfect and imperfect information games, as well as traditional multiagent environments such as (partially- and fully- observable) grid worlds and social dilemmas. OpenSpiel also includes tools to… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms
    • 60
    • PDF
    A Generalized Training Approach for Multiagent Learning
    • 10
    • PDF
    RLCard: A Toolkit for Reinforcement Learning in Card Games
    • 7
    • PDF
    Learning to Play No-Press Diplomacy with Best Response Policy Iteration
    • 3
    • PDF
    From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization
    • 6
    • PDF
    Physically Embedded Planning Problems: New Challenges for Reinforcement Learning
    • 2
    • PDF
    Navigating the Landscape of Games
    • 1
    Neural Replicator Dynamics: Multiagent Learning via Hedging Policy Gradients
    Real World Games Look Like Spinning Tops
    • 2
    • PDF


    Publications referenced by this paper.
    Markov Games as a Framework for Multi-Agent Reinforcement Learning
    • 1,803
    • PDF
    A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
    • 207
    • PDF
    Deep Reinforcement Learning from Self-Play in Imperfect-Information Games
    • 129
    • PDF
    Multiagent Systems - Algorithmic, Game-Theoretic, and Logical Foundations
    • 1,777
    • PDF
    A Multiagent Reinforcement Learning Algorithm with Non-linear Dynamics
    • 73
    • PDF
    Reinforcement Learning: An Introduction
    • 25,507
    • Highly Influential
    • PDF