{
  "abstract": "In this work, we study radically uncoupled learning in discounted general-sum Markov games. Assuming ``$\\mathsf{ETH}$ for $\\mathsf{PPAD}$\", we show that, for every fixed discount factor, there is no polynomial-time algorithm for computing inverse-polynomially accurate coarse correlated equilibria in discounted general-sum Markov games when players learn independently in decentralized settings. Complementing this hardness result, we provide what appears to be the first \\emph{radically uncoupled} algorithm with sub-exponential convergence guarantees to coarse correlated equilibria in discounted general-sum Markov games without imposing any structural restrictions on the game. Our algorithm is a \\emph{layered} variant of optimistic mirror descent with an increasing step-size schedule tailored to the multi-agent setting. Finally, we develop both full-feedback and partial feedback versions of the aforementioned algorithm and establish sub-exponential convergence guarantees for each case.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.00504",
  "author_total": 3,
  "authors": [
    {
      "name": "Asrin Efe Yorulmaz"
    },
    {
      "name": "Ugur Aydin"
    },
    {
      "name": "Tamer Basar"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/c555gqb1vqh5x.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.00504",
  "fulltext_url": null,
  "id": "c555gqb1vqh5x",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.00504",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.GT"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "cs.SY"
    ],
    [
      "arxiv",
      "eess.SY"
    ],
    [
      "arxiv",
      "math.OC"
    ],
    [
      "openalex",
      "1803|Game Theory and Applications"
    ]
  ],
  "openalex": "W7206177426",
  "pdf_url": "https://arxiv.org/pdf/2609.00504",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/c555gqb1vqh5x.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:04Z",
      "native_id": "2609.00504",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.00504"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Independent Reinforcement Learning in Discounted Markov Games",
  "title_text": "Independent Reinforcement Learning in Discounted Markov Games",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:04Z",
  "url": "https://research.draconitic.com/paper/c555gqb1vqh5x",
  "venue": "arXiv",
  "versions": []
}