{
  "id": "2403.07979",
  "version": "v1",
  "published": "2024-03-12T18:00:02.000Z",
  "updated": "2024-03-12T18:00:02.000Z",
  "title": "Do Agents Dream of Electric Sheep?: Improving Generalization in Reinforcement Learning through Generative Learning",
  "authors": [
    "Giorgio Franceschelli",
    "Mirco Musolesi"
  ],
  "categories": [
    "cs.LG",
    "cs.AI"
  ],
  "abstract": "The Overfitted Brain hypothesis suggests dreams happen to allow generalization in the human brain. Here, we ask if the same is true for reinforcement learning agents as well. Given limited experience in a real environment, we use imagination-based reinforcement learning to train a policy on dream-like episodes, where non-imaginative, predicted trajectories are modified through generative augmentations. Experiments on four ProcGen environments show that, compared to classic imagination and offline training on collected experience, our method can reach a higher level of generalization when dealing with sparsely rewarded environments.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-03-12T18:00:02.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "reinforcement learning",
      "agents dream",
      "electric sheep",
      "improving generalization",
      "generative learning"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}