Evaluation And Learning In Two-player Symmetric Games Via Best And Better Responses

Abstract

Artificial intelligence and robotic competitions are accompanied by a class of game paradigms in which each player privately commits a strategy to a game system which simulates the game using the collected joint strategy and then returns payoffs to players. This paper considers the strategy commitment for two-player symmetric games in which the players' strategy spaces are identical and their payoffs are symmetric. First, we introduce two digraph-based metrics at a meta-level for strategy evaluation in two-agent reinforcement learning, grounded on sink equilibrium. The metrics rank the strategies of a single player and determine the set of strategies which are preferred for the private commitment. Then, in order to find the preferred strategies under the metrics, we propose two variants of the classical learning algorithm self-play, called strictly best-response and weakly better-response self-plays. By modeling learning processes as walks over joint-strategy response digraphs, we prov

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyan2022evaluation

Related papers

• Policy Evaluation And Seeking For Multi-agent Reinforcement Learning Via Best Response (2020)0.00
• Reinforcement Learning In Two Player Zero Sum Simultaneous Action Games (2021)0.00
• Approximate Exploitability: Learning A Best Response In Large Games (2020)0.00
• Asymmetric Nash Seeking Via Best Response Maps: Global Linear Convergence And Robustness To Inexact Reaction Models (2026)0.00
• Learning To Play No-press Diplomacy With Best Response Policy Iteration (2020)0.00
• Choosing Well Your Opponents: How To Guide The Synthesis Of Programmatic Strategies (2023)3.58
• Actor-dual-critic Dynamics For Zero-sum And Identical-interest Stochastic Games (2026)0.00
• Efficient Competitive Self-play Policy Optimization (2020)0.00