{
  "abstract": "While self-supervised Contrastive Reinforcement Learning (CRL) has shown remarkable depth-scaling capabilities, successfully using networks over 64 layers, scaled CRL still struggles with long-horizon goal-conditioned planning due to the uniformity-tolerance dilemma inherent in contrastive losses. We introduce Survival Reinforcement Learning (SRL), an online classification-based alternative that extends the survival value learning framework by maximizing the agent's dwell time at target goals. SRL bypasses the structural constraints of CRL and mitigates the \"bang-bang\" control solutions inherent to survival frameworks, which often induce undesirable behavior in complex dynamical systems. Evaluated across diverse robotic benchmarks, scaled SRL matches state-of-the-art CRL on manipulation tasks and outperforms it by 2x to 8x on stable, long-horizon locomotion tasks. Our results provide strong additional evidence that classification-based methods may serve as a key primitive in the broader effort to scale reinforcement learning and an open-source implementation is available online: https://github.com/Simple-Robotics/survival-reinforcement-learning.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2605.31273",
  "author_total": 4,
  "authors": [
    {
      "name": "Franki Nguimatsia-Tiofack"
    },
    {
      "name": "Fabian Schramm"
    },
    {
      "name": "Théotime Le Hellard"
    },
    {
      "name": "Justin Carpentier"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/e6ej7w3ppzb67.bib",
  "cited_by": 0,
  "doi": null,
  "fulltext_url": null,
  "id": "e6ej7w3ppzb67",
  "issns": [],
  "landing_url": "https://hal.science/hal-05649866v2",
  "language": "en",
  "licence": "CC-BY-NC-SA-4.0",
  "licence_label": "CC BY-NC-SA 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-sa/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "hal",
      "0.info"
    ],
    [
      "hal",
      "0.scco"
    ],
    [
      "hal",
      "0.stat"
    ],
    [
      "hal",
      "1.info.info-lg"
    ],
    [
      "hal",
      "1.info.info-rb"
    ],
    [
      "hal",
      "1.scco.comp"
    ],
    [
      "hal",
      "1.stat.ml"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://hal.science/hal-05649866/document",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-18",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/e6ej7w3ppzb67.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:36Z",
      "native_id": "hal-05649866",
      "source": "hal",
      "url": "https://hal.science/hal-05649866v2"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "hal:0.stat",
      "subfield": "statistics"
    }
  ],
  "title": "Survival Reinforcement Learning: Toward Scalable Self-Supervised RL",
  "title_text": "Survival Reinforcement Learning: Toward Scalable Self-Supervised RL",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:36Z",
  "url": "https://research.draconitic.com/paper/e6ej7w3ppzb67",
  "venue": "HAL",
  "versions": []
}