{
  "abstract": "Inverse game theory seeks to learn agents' unknown objectives from observed equilibrium behavior. Existing residual-based approaches can lead to non-convex problems and need not ensure strong monotonicity of the learned game, limiting reliable equilibrium prediction. We develop a tractable convex framework for learning static and dynamic non-cooperative games using first-order and Nikaido-Isoda (NI) loss. Specialized operator parameterizations, including a Helmholtz--Hodge decomposition in a reproducing kernel Hilbert space (RKHS), enforce strong monotonicity for quadratic, nonparametric, non-quadratic, and linear-quadratic dynamic games. We establish finite-sample out-of-sample prediction guarantees, using Rademacher complexity to match existing bounds for the non-quadratic setting. For noisy sequential data, we develop a robust receding-horizon learning scheme whose adaptive regularization admits a maximum a posteriori (MAP) interpretation and is computed using randomized trace estimation. Numerical experiments, including a stylized autonomous-vehicle collision-avoidance application, demonstrate predictive accuracy and robustness to measurement noise.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.03481",
  "author_total": 4,
  "authors": [
    {
      "name": "Arghya Mallick"
    },
    {
      "name": "Reza Rahimi Baghbadorani"
    },
    {
      "name": "Peyman Mohajerin Esfahani"
    },
    {
      "name": "Sergio Grammatico"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cbf4w9ypdyj1n.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.03481",
  "fulltext_url": null,
  "id": "cbf4w9ypdyj1n",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.03481",
  "language": null,
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.SY"
    ],
    [
      "arxiv",
      "eess.SY"
    ],
    [
      "arxiv",
      "math.OC"
    ],
    [
      "openalex",
      "1803|Game Theory and Applications"
    ]
  ],
  "openalex": "W7220476842",
  "pdf_url": "https://arxiv.org/pdf/2610.03481",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cbf4w9ypdyj1n.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:50Z",
      "native_id": "2610.03481",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.03481"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Learning in Inverse Games: Tractable Training with Probabilistic Guarantees",
  "title_text": "Learning in Inverse Games: Tractable Training with Probabilistic Guarantees",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:50Z",
  "url": "https://research.draconitic.com/paper/cbf4w9ypdyj1n",
  "venue": "arXiv",
  "versions": []
}