{
  "annotation_id": "94827e15-b024-4380-bb4e-706e3c62dbc2",
  "date_created": "2026-02-17T05:53:11.278000Z",
  "date_modified": "2026-02-17T05:53:11.278000Z",
  "file_hash": "7d55fac4d3ffaf2ad85bb447ab2f9e76960d5a82a4cbf628d4e4de0ad1df4fe8",
  "private": false,
  "record": {
    "abstract": "Adversarial robustness in RL is difficult because perturbations affect entire trajectories: strong attacks can break learning, while weak attacks yield little robustness, and the appropriate strength varies by state. We propose $\\alpha$-reward-preserving attacks, which adapt the strength of the adversary so that an $\\alpha$ fraction of the nominal-to-worst-case return gap remains achievable at each state. In deep RL, we use a gradient-based attack direction and learn a state-dependent magnitude $\\eta\\le \\eta_{\\mathcal B}$ selected via a critic $Q^{\\pi}_\\alpha((s,a),\\eta)$ trained off-policy over diverse radii. This adaptive tuning calibrates attack strength and, with intermediate $\\alpha$, improves robustness across radii while preserving nominal performance, outperforming fixed- and random-radius baselines.",
    "arxiv_id": "2601.07118",
    "authors": [
      "Lucas Schott",
      "Elies Gherbi",
      "Hatem Hajri",
      "Sylvain Lamprier"
    ],
    "categories": [
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "Reward-Preserving Attacks For Robust Reinforcement Learning",
    "url": "https://arxiv.org/abs/2601.07118",
    "version": "v2"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "494b46b6-89b1-4bbe-9059-0b50ce1c5022",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}