{
  "id": "1810.12282",
  "version": "v1",
  "published": "2018-10-29T17:51:46.000Z",
  "updated": "2018-10-29T17:51:46.000Z",
  "title": "Assessing Generalization in Deep Reinforcement Learning",
  "authors": [
    "Charles Packer",
    "Katelyn Gao",
    "Jernej Kos",
    "Philipp Krähenbühl",
    "Vladlen Koltun",
    "Dawn Song"
  ],
  "comment": "18 pages, 6 figures",
  "categories": [
    "cs.LG",
    "cs.AI",
    "stat.ML"
  ],
  "abstract": "Deep reinforcement learning (RL) has achieved breakthrough results on many tasks, but has been shown to be sensitive to system changes at test time. As a result, building deep RL agents that generalize has become an active research area. Our aim is to catalyze and streamline community-wide progress on this problem by providing the first benchmark and a common experimental protocol for investigating generalization in RL. Our benchmark contains a diverse set of environments and our evaluation methodology covers both in-distribution and out-of-distribution generalization. To provide a set of baselines for future research, we conduct a systematic evaluation of deep RL algorithms, including those that specifically tackle the problem of generalization.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-10-29T17:51:46.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep reinforcement learning",
      "assessing generalization",
      "evaluation methodology covers",
      "building deep rl agents",
      "deep rl algorithms"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 18,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}