2601.18907v1.pdf

{
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "00d4cf4a28843a8061196a5e4341bf63fbca7e4fe409a062d06e292b63f6708c",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.18907v1.pdf",
      "size": 1432637
    },
    "source": {
      "execution_id": "846d2068-5bb3-4dbd-b174-01fa7ed76b01",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 46,
      "producer": "pikepdf 8.15.1",
      "title": "Implicit Q-Learning and SARSA: Liberating Policy Control from Step-Size Calibration",
      "version": "1.7"
    },
    "source": {
      "execution_id": "c7381f9e-c8f5-4729-aa3d-0b3ef734f6f1",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}