{
  "id": "2211.15457",
  "version": "v2",
  "published": "2022-11-28T15:48:35.000Z",
  "updated": "2023-01-02T20:14:02.000Z",
  "title": "Hypernetworks for Zero-shot Transfer in Reinforcement Learning",
  "authors": [
    "Sahand Rezaei-Shoshtari",
    "Charlotte Morissette",
    "Francois Robert Hogan",
    "Gregory Dudek",
    "David Meger"
  ],
  "comment": "AAAI 2023",
  "categories": [
    "cs.LG"
  ],
  "abstract": "In this paper, hypernetworks are trained to generate behaviors across a range of unseen task conditions, via a novel TD-based training objective and data from a set of near-optimal RL solutions for training tasks. This work relates to meta RL, contextual RL, and transfer learning, with a particular focus on zero-shot performance at test time, enabled by knowledge of the task parameters (also known as context). Our technical approach is based upon viewing each RL algorithm as a mapping from the MDP specifics to the near-optimal value function and policy and seek to approximate it with a hypernetwork that can generate near-optimal value functions and policies, given the parameters of the MDP. We show that, under certain conditions, this mapping can be considered as a supervised learning problem. We empirically evaluate the effectiveness of our method for zero-shot transfer to new reward and transition dynamics on a series of continuous control tasks from DeepMind Control Suite. Our method demonstrates significant improvements over baselines from multitask and meta RL approaches.",
  "revisions": [
    {
      "version": "v2",
      "updated": "2023-01-02T20:14:02.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "zero-shot transfer",
      "reinforcement learning",
      "hypernetwork",
      "method demonstrates significant improvements",
      "generate near-optimal value functions"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}