{
  "abstract": "While offline reinforcement learning (RL) enables policy optimization from static datasets without costly online interaction, it remains bottlenecked by the risk of executing out-of-distribution (OOD) actions. Recent approaches mitigate this by learning a behavior-cloning policy through flow matching and then performing RL within its constrained latent space. However, naively optimizing the latent policy can easily cause the policy to collapse into a brittle mode or exploit sharp artifacts of the learned critic. In this work, we find that entropy regularization is essential in latent-space RL for addressing these challenges. We introduce LASER, a novel offline RL algorithm that applies latent-space adjoint matching to achieve entropy-regularized latent-space RL with expressive flow policies while avoiding backpropagation through time. Through comprehensive experiments on 40 challenging OGBench tasks with varying dataset qualities, we show that LASER achieves state-of-the-art performance. Notably, LASER uses fixed method-specific hyperparameters across all tasks and outperforms the evaluated baselines, including those with task- and dataset-specific tuning, which highlights the robust applicability of LASER. Project website: https://mit-realm.github.io/laser/.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.08989",
  "author_total": 6,
  "authors": [
    {
      "name": "Songyuan Zhang"
    },
    {
      "name": "Oswin So"
    },
    {
      "name": "Eric Yang Yu"
    },
    {
      "name": "Matthew Cleaveland"
    },
    {
      "name": "Peter Crowley-Dolen"
    },
    {
      "name": "Chuchu Fan"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4aerhqxkvq6k8.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.08989",
  "fulltext_url": null,
  "id": "4aerhqxkvq6k8",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.08989",
  "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.LG"
    ],
    [
      "arxiv",
      "cs.RO"
    ],
    [
      "arxiv",
      "math.OC"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Reinforcement Learning in Robotics"
    ]
  ],
  "openalex": "W7220928305",
  "pdf_url": "https://arxiv.org/pdf/2610.08989",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/4aerhqxkvq6k8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:54Z",
      "native_id": "2610.08989",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.08989"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    },
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL",
  "title_text": "LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL",
  "type": "preprint",
  "updated_at": "2026-10-30T12:30:00Z",
  "url": "https://research.draconitic.com/paper/4aerhqxkvq6k8",
  "venue": "arXiv",
  "versions": []
}