{
  "abstract": "Existing approaches to offline goal-conditioned reinforcement learning (GCRL) struggle with long-horizon tasks. Discounting shrinks value differences between distant states until they fall below the function approximation error, leaving the agent with no signal for ranking states. Temporal abstraction, which treats k environment steps as a single transition, restores this signal at long range, but no single fixed k suits all state-goal distances: large k preserves value differences across long temporal distances while collapsing distinctions between nearby states, and small k does the reverse. We make this trade-off explicit and introduce Generalized Implicit Temporal Abstraction (GITA), which conditions a single value function on k. GITA trains one policy by aggregating advantage-weighted supervision across multiple k values, so scales assigning larger positive advantages to a state-goal pair contribute more strongly to its update. GITA does not need to choose between local resolution and long-range signal; it retains both without committing to a single k. On OGBench, GITA outperforms a broad range of offline GCRL baselines, raising average success rate across all tasks by 25 percentage points (73% relative improvement) over HIQL. It also improves over the strongest fixed-k method, OTA, by 7 percentage points (14% relative).",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.00849",
  "author_total": 4,
  "authors": [
    {
      "name": "Pedro Robles Dutenhefner"
    },
    {
      "name": "Dikshant Shehmar"
    },
    {
      "name": "Wagner Meira Jr."
    },
    {
      "name": "Marlos C. Machado"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/89xtjp7b6qm0y.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.00849",
  "fulltext_url": null,
  "id": "89xtjp7b6qm0y",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.00849",
  "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",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Reinforcement Learning in Robotics"
    ]
  ],
  "openalex": "W7216369034",
  "pdf_url": "https://arxiv.org/pdf/2610.00849",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/89xtjp7b6qm0y.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:14Z",
      "native_id": "2610.00849",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.00849"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Learning Multiple Timescales for Goal-Conditioned Reinforcement Learning",
  "title_text": "Learning Multiple Timescales for Goal-Conditioned Reinforcement Learning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:14Z",
  "url": "https://research.draconitic.com/paper/89xtjp7b6qm0y",
  "venue": "arXiv",
  "versions": []
}