{
  "abstract": "The inherent non-convex minimum-separation constraints introduced by movable antennas present a formidable challenge to the joint optimization of antenna positions and transmission strategies, rendering conventional methods computationally infeasible, particularly in large-scale cell-free massive multiple-input multiple-output (MIMO). In this work, we propose the graph-based learning individual intrinsic reward heterogeneous-agent proximal policy optimization (GLIIR-HAPPO) algorithm, a novel heterogeneous multi-agent reinforcement learning (MARL) framework that fundamentally overcomes this impasse by systematically decomposing the original coupled optimization into coordinated subproblems. To ensure tractability, we embed the non-convex geometric constraints into a penalty-augmented reward structure and develop a specialized geometric solver that enables the positioning agents to efficiently navigate the high-dimensional action space. Specifically, we propose an architecture featuring a dynamic-interaction graph critic for adaptive cross-role coordination, together with role-conditioned federated distillation that synchronizes same-role policies through compact actor-output statistics. Beyond architectural design, we establish a rigorous theoretical analysis that derives monotonic performance improvement bounds and establishes convergence guarantees for the proposed bi-level optimization. Numerical simulations demonstrate that our framework yields significant sum-rate improvements over state-of-the-art MARL schemes. Moreover, the performance of our advanced architecture closely approaches its fully centralized counterpart, while drastically reducing communication overhead.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.08387",
  "author_total": 7,
  "authors": [
    {
      "name": "Bokai Xu"
    },
    {
      "name": "Jiayi Zhang"
    },
    {
      "name": "Shuaifei Chen"
    },
    {
      "name": "Ziheng Liu"
    },
    {
      "name": "Huahua Xiao"
    },
    {
      "name": "Derrick Wing Kwan Ng"
    },
    {
      "name": "Bo Ai"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/132t7e2kpz73v.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.08387",
  "fulltext_url": null,
  "id": "132t7e2kpz73v",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.08387",
  "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.IT"
    ],
    [
      "arxiv",
      "math.IT"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2610.08387",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-06",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/132t7e2kpz73v.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:26Z",
      "native_id": "2610.08387",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.08387"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.IT",
      "subfield": "general"
    }
  ],
  "title": "Multi-Agent Reinforcement Learning for Movable Antenna-aided Cell-Free Massive MIMO Systems",
  "title_text": "Multi-Agent Reinforcement Learning for Movable Antenna-aided Cell-Free Massive MIMO Systems",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:26Z",
  "url": "https://research.draconitic.com/paper/132t7e2kpz73v",
  "venue": "arXiv",
  "versions": []
}