{
  "abstract": "Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single variational principle. We frame AIF as policy optimization and show that, for closed-loop control policies, EFE minimization can be formulated as a convex Markov decision process (MDP). This perspective reveals that policy-dependent reward prediction errors transmit natural gradients of the expected free energy backwards in time rather than up a hierarchy. Finally, we show that coupling world-model learning with policy optimization gives active inference the structure of performative reinforcement learning. Together this places EFE minimization within modern reinforcement learning and optimization theory and opens a route toward principled algorithms for active inference.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2607.20152",
  "author_total": 3,
  "authors": [
    {
      "name": "Nikola Milosevic"
    },
    {
      "name": "Nicolás Hinrichs"
    },
    {
      "name": "Nico Scherf"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9g3v0bk0zrax2.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2607.20152",
  "fulltext_url": null,
  "id": "9g3v0bk0zrax2",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2607.20152",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "2805|Embodied and Extended Cognition"
    ]
  ],
  "openalex": "W7170181775",
  "pdf_url": "https://arxiv.org/pdf/2607.20152",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-13",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9g3v0bk0zrax2.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:26Z",
      "native_id": "2607.20152",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2607.20152"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Active Inference as a Convex Markov Decision Process",
  "title_text": "Active Inference as a Convex Markov Decision Process",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:26Z",
  "url": "https://research.draconitic.com/paper/9g3v0bk0zrax2",
  "venue": "arXiv",
  "versions": []
}