{
  "abstract": "Learning flexible motor primitives is a hallmark of skilled motor control. Recent neuroscience theory proposes that motor primitives may be implemented as low-rank perturbations of a shared recurrent network, but leaves open how such a system is learned. We translate this principle into a novel architecture for learning motor skills end-to-end: a shared recurrent core modulated by a bank of residual adapters, each selected by a discrete latent code. Trained on closed-loop biomechanical control, the adapters develop emergent low-rank perturbations of the recurrent dynamics despite no architectural rank constraint, placing task representations in disparate subspaces of the shared core network. A simple high-level policy over the learned options, optimized while the whole network is frozen, sequences the low-rank adapters to produce novel out-of-distribution movements. We demonstrate the ability to generalize to novel motor sequences within the closed-loop control setting, improving on the generalization error of a task-input-conditioned multitask baseline by upto order of magnitude.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.17042",
  "author_total": 3,
  "authors": [
    {
      "name": "Sreejan Kumar"
    },
    {
      "name": "Marcelo Mattar"
    },
    {
      "name": "Lea Duncker"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0kdybe00937ye.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.17042",
  "fulltext_url": null,
  "id": "0kdybe00937ye",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.17042",
  "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.LG"
    ],
    [
      "arxiv",
      "cs.RO"
    ],
    [
      "arxiv",
      "q-bio.NC"
    ],
    [
      "openalex",
      "1702|Reinforcement Learning in Robotics"
    ]
  ],
  "openalex": "W7213409181",
  "pdf_url": "https://arxiv.org/pdf/2609.17042",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0kdybe00937ye.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:46Z",
      "native_id": "2609.17042",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.17042"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.NC",
      "subfield": "neuroscience"
    }
  ],
  "title": "Learning Options for Compositional Motor Control with Adapter Banks",
  "title_text": "Learning Options for Compositional Motor Control with Adapter Banks",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:46Z",
  "url": "https://research.draconitic.com/paper/0kdybe00937ye",
  "venue": "arXiv",
  "versions": []
}