Game Theoretic Rating in N-player general-sum games with Equilibria
Not on the map. Why?
Abstract (arXiv)
Rating strategies in a game is an important area of research in game theory and artificial intelligence, and can be applied to any real-world competitive or cooperative setting. Traditionally, only transitive dependencies between strategies have been used to rate strategies (e.g. Elo), however recent work has expanded ratings to utilize game theoretic solutions to better rate strategies in non-transitive games. This work generalizes these ideas and proposes novel algorithms suitable for N-player, general-sum rating of strategies in normal-form games according to the payoff rating system. This enables well-established solution concepts, such as equilibria, to be leveraged to efficiently rate strategies in games with complex strategic interactions, which arise in multiagent training and real-world interactions between many agents. We empirically validate our methods on real world normal-form data (Premier League) and multiagent reinforcement learning agent evaluation.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 25 of its 57 references that are in the map. First posted on arXiv 5 Oct 2022.
Builds on
25 of 57 references.
References · 25
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
- 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
- 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 555
- 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 265
- 2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 260
- 2019OpenSpiel: A Framework for Reinforcement Learning in Gamescited by 180
- 2018A Survey and Critique of Multiagent Deep Reinforcement Learningcited by 173
- 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 153
- 2017Emergent Complexity via Multi-Agent Competitioncited by 117
- 2019Open-ended Learning in Symmetric Zero-sum Gamescited by 96
- 2017A Survey of Learning in Multiagent Environments: Dealing with Non-Stationaritycited by 93
- 2020Real World Games Look Like Spinning Topscited by 66
13 more
- 2019Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Researchcited by 58
- 2019A Generalized Training Approach for Multiagent Learningcited by 53
- 2019α-Rank: Multi-Agent Evaluation by Evolutioncited by 50
- 2018Re-evaluating Evaluationcited by 47
- 2020EigenGame: PCA as a Nash Equilibriumcited by 39
- 2018Actor-Critic Policy Optimization in Partially Observable Multiagent Environmentscited by 35
- 2020Learning to Play No-Press Diplomacy with Best Response Policy Iterationcited by 25
- 2019Correlation in Extensive-Form Games: Saddle-Point Formulation and Benchmarkscited by 23
- 2021Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solverscited by 21
- 2019Coarse Correlation in Extensive-Form Gamescited by 17
- 2019Multiagent Evaluation under Incomplete Informationcited by 13
- 2021Sample-based Approximation of Nash in Large Many-Player Games via Gradient Descentcited by 11
- 2021Estimating α-Rank by Maximizing Information Gaincited by 4
Built on by
Citing papers per year: 2023: 2; 2024: 0; 2025: 1.
3 papers.