paper
Regret Minimization with Adaptive Opponents in Repeated Games
paperactiveprovisional
regret-minimization-with-adaptive-opponents-in-repeated-games-514f5b61·1 events·first seen 12d agoAliases: Regret Minimization with Adaptive Opponents in Repeated Games
Co-occurring entities
More like this (12)
Repeated Policy Regret (RP-Regret)Invariant Risk MinimizationMulti-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided DispatchDNQ: Deep Nash Q-Network for Partially Observable n-Player GamesIterated Prisoner's DilemmaGame-Theoretic EquilibriaEntropy-Regularized Reinforcement LearningAlgorithmic and Minimax Complexities in Kernel Banditsadversarial refinementUsing Reward Uncertainty to Induce Diverse Behaviour in Reinforcement LearningIn-Context Reward Adaptationadversarial robustness
Recent events (1)
Repeated Policy Regret (RP-Regret): Regret minimization against adaptive opponents in repeated games
This arXiv paper introduces Repeated Policy Regret (RP-Regret), a new game-theoretic metric for regret minimization in repeated games where opponents can adapt based on play history — a setting where standard external regret fails. The authors prove necessary conditions for sublinear RP-Regret and propose three algorithms to minimize it, including oracle-based, linearized surrogate, and slow-opponent variants. When all players minimize RP-Regret, certain subgame perfect equilibria can be learned, and experiments show more cooperative outcomes in games like Stag-Hunt.