{
  "name": "OpenSpiel Standard Game Environments and Structural Properties",
  "description": "Comparative dataset of canonical game environments implemented in Google DeepMind's OpenSpiel framework, detailing player dynamics, information availability, payoff structure, approximate game tree state space, and standard evaluation metrics compiled from official documentation and the foundational OpenSpiel specification.",
  "page": "https://casrai.org/guides/openspiel",
  "publisher": "CASRAI",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "dateModified": "2026-11-16T22:04:40Z",
  "temporalCoverage": "2019/2026",
  "spatialCoverage": "Global",
  "columns": [
    {
      "name": "Environment",
      "unit": "",
      "description": "Canonical game identifier in OpenSpiel"
    },
    {
      "name": "Information Type",
      "unit": "",
      "description": "Perfect or imperfect information availability"
    },
    {
      "name": "Player Count",
      "unit": "players",
      "description": "Number of decision-making participants"
    },
    {
      "name": "Turn Dynamics",
      "unit": "",
      "description": "Sequential, simultaneous, or normal-form turns"
    },
    {
      "name": "Payoff Structure",
      "unit": "",
      "description": "Zero-sum, general-sum, or cooperative payoff distribution"
    },
    {
      "name": "Game Tree State Size",
      "unit": "log10 states",
      "description": "Logarithmic order of magnitude of game tree state space"
    },
    {
      "name": "Primary Evaluation Metric",
      "unit": "",
      "description": "Standard computational metric used to evaluate agent performance"
    }
  ],
  "rows": [
    {
      "Environment": "Kuhn Poker",
      "Information Type": "Imperfect",
      "Player Count": 2,
      "Turn Dynamics": "Sequential",
      "Payoff Structure": "Zero-sum",
      "Game Tree State Size": 2,
      "Primary Evaluation Metric": "Exploitability"
    },
    {
      "Environment": "Leduc Hold'em",
      "Information Type": "Imperfect",
      "Player Count": 2,
      "Turn Dynamics": "Sequential",
      "Payoff Structure": "Zero-sum",
      "Game Tree State Size": 6,
      "Primary Evaluation Metric": "Exploitability"
    },
    {
      "Environment": "Tic-Tac-Toe",
      "Information Type": "Perfect",
      "Player Count": 2,
      "Turn Dynamics": "Sequential",
      "Payoff Structure": "Zero-sum",
      "Game Tree State Size": 4,
      "Primary Evaluation Metric": "Minimax / Optimal Policy"
    },
    {
      "Environment": "Connect Four",
      "Information Type": "Perfect",
      "Player Count": 2,
      "Turn Dynamics": "Sequential",
      "Payoff Structure": "Zero-sum",
      "Game Tree State Size": 14,
      "Primary Evaluation Metric": "AlphaZero / MCTS Win Rate"
    },
    {
      "Environment": "Breakthrough",
      "Information Type": "Perfect",
      "Player Count": 2,
      "Turn Dynamics": "Sequential",
      "Payoff Structure": "Zero-sum",
      "Game Tree State Size": 25,
      "Primary Evaluation Metric": "AlphaZero / Elo Rating"
    },
    {
      "Environment": "Go (19x19)",
      "Information Type": "Perfect",
      "Player Count": 2,
      "Turn Dynamics": "Sequential",
      "Payoff Structure": "Zero-sum",
      "Game Tree State Size": 170,
      "Primary Evaluation Metric": "AlphaZero / Elo Rating"
    },
    {
      "Environment": "Matrix Prisoner's Dilemma",
      "Information Type": "Imperfect",
      "Player Count": 2,
      "Turn Dynamics": "Simultaneous",
      "Payoff Structure": "General-sum",
      "Game Tree State Size": 1,
      "Primary Evaluation Metric": "Social Welfare / Defection Rate"
    },
    {
      "Environment": "Hanabi",
      "Information Type": "Imperfect",
      "Player Count": 5,
      "Turn Dynamics": "Sequential",
      "Payoff Structure": "Cooperative",
      "Game Tree State Size": 13,
      "Primary Evaluation Metric": "Average Cooperative Score"
    }
  ],
  "sources": [
    {
      "title": "OpenSpiel GitHub Repository, Google DeepMind",
      "url": "https://github.com/google-deepmind/open_spiel",
      "accessed": "2026-11-16"
    },
    {
      "title": "OpenSpiel: A Framework for Reinforcement Learning in Games (arXiv:1908.09453)",
      "url": "https://arxiv.org/abs/1908.09453",
      "accessed": "2026-11-16"
    },
    {
      "title": "OpenSpiel Read the Docs Documentation",
      "url": "https://openspiel.readthedocs.io/",
      "accessed": "2026-11-16"
    }
  ]
}