{"paper":{"title":"Learning Equilibria in Coordination Games via Minorization-Maximization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Regularizing coordination games with irrational individual costs creates a unique equilibrium that a minorization-maximization scheme can learn reliably.","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Ana Busic, Ashok Krishnan K.S., Helene Le Cadre","submitted_at":"2026-05-13T15:06:06Z","abstract_excerpt":"This paper considers games where the utilities for agents are the sum of a term proportional to a social utility, and another term that is an individual cost or reward. The agents are assumed to be irrational in their perception of the individual cost or reward. The multi equilibrium game is regularized, and its strictly concave potential function is used to select a unique equilibrium. This selected equilibrium is shown to be an $\\epsilon-$equilibrium of the original game, where $\\epsilon$ is parametrized by the regularizing function. A minorization-maximization based iterative learning schem"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"This selected equilibrium is shown to be an ε-equilibrium of the original game, where ε is parametrized by the regularizing function. A minorization-maximization based iterative learning scheme is proposed to learn equilibria in this game. This scheme converges to the potential-optimal equilibrium, and has superior convergence behaviour in comparison to gradient and best response methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The multi-equilibrium game can be regularized so that it possesses a strictly concave potential function that selects a unique equilibrium; the agents' irrational perception of individual costs is modeled in a way that preserves the potential-game structure after regularization.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Regularizing multi-equilibrium coordination games with a strictly concave potential selects a unique epsilon-equilibrium that a minorization-maximization scheme learns with faster convergence than standard alternatives.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Regularizing coordination games with irrational individual costs creates a unique equilibrium that a minorization-maximization scheme can learn reliably.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"80fcf4e7f4dab737088ed926efa0fdc51b4c6e594f37ab1f792b73c1b24ed7fe"},"source":{"id":"2605.13644","kind":"arxiv","version":1},"verdict":{"id":"dcb34a76-27f7-4d6e-bd6d-592bf37b73ea","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:14:48.601365Z","strongest_claim":"This selected equilibrium is shown to be an ε-equilibrium of the original game, where ε is parametrized by the regularizing function. A minorization-maximization based iterative learning scheme is proposed to learn equilibria in this game. This scheme converges to the potential-optimal equilibrium, and has superior convergence behaviour in comparison to gradient and best response methods.","one_line_summary":"Regularizing multi-equilibrium coordination games with a strictly concave potential selects a unique epsilon-equilibrium that a minorization-maximization scheme learns with faster convergence than standard alternatives.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The multi-equilibrium game can be regularized so that it possesses a strictly concave potential function that selects a unique equilibrium; the agents' irrational perception of individual costs is modeled in a way that preserves the potential-game structure after regularization.","pith_extraction_headline":"Regularizing coordination games with irrational individual costs creates a unique equilibrium that a minorization-maximization scheme can learn reliably."},"references":{"count":39,"sample":[{"doi":"","year":1999,"title":"R. Cooper, Coordination games. Cambridge university Press, 1999","work_id":"3d83a558-e71b-4ff1-a085-fd44aada9ae8","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2010,"title":"Aggregative games and best-reply potenti als,","work_id":"d849236d-4716-444b-936d-b99fcb32aa2f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1999,"title":"Voorneveld, Potential games and interactive decisions with multiple cr iteria","work_id":"cbc36c77-093b-4c66-a5e1-f1fa2398b7d5","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Achieving a Collective Target through In- centives,","work_id":"80c3f319-ea49-443e-98b0-7fc671da8660","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Exploration in deep reinforcement learning: From single-agent to multi agent domain,","work_id":"54fc7324-7ebb-4967-a164-43aa1d60a8c8","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":39,"snapshot_sha256":"f17fb7f26318562150c31aecab7c5c2598a93ad2d0407505de89ad0f003f6c7a","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3609097eeef36aa478b3cbd43b1cc6e8bdc61bd60f070e2f20cc922fca79ed68"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}