{"paper":{"title":"Regret Minimization with Adaptive Opponents in Repeated Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.LG","authors_text":"Asuman Ozdaglar, Kaiqing Zhang, Mingyang Liu, Tiancheng Yu","submitted_at":"2026-06-04T17:59:08Z","abstract_excerpt":"In this paper, we study regret minimization in repeated games with \\emph{adaptive} opponents who can respond based on histories of play. The standard metric of \\emph{external regret} in online learning is known to fail to capture such adaptivity. To account for players' counterfactual reasoning, we introduce {\\tt Repeated Policy Regret (RP-Regret)}, a game-theoretic metric that measures the difference between the \\emph{realized} and the \\emph{best-in-hindsight} accumulated utility when all players can \\emph{respond} to the history of play. Compared to existing regret notions in this setting, o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06486","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.06486/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}