{
  "id": "1810.06530",
  "version": "v1",
  "published": "2018-10-15T17:30:53.000Z",
  "updated": "2018-10-15T17:30:53.000Z",
  "title": "Successor Uncertainties: exploration and uncertainty in temporal difference learning",
  "authors": [
    "David Janz",
    "Jiri Hron",
    "José Miguel Hernández-Lobato",
    "Katja Hofmann",
    "Sebastian Tschiatschek"
  ],
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "We consider the problem of balancing exploration and exploitation in sequential decision making problems. To explore efficiently, it is vital to consider the uncertainty over all consequences of a decision, and not just those that follow immediately; the uncertainties involved need to be propagated according to the dynamics of the problem. To this end, we develop Successor Uncertainties, a probabilistic model for the state-action value function of a Markov Decision Process that propagates uncertainties in a coherent and scalable way. We relate our approach to other classical and contemporary methods for exploration and present an empirical analysis.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-10-15T17:30:53.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "uncertainty",
      "successor uncertainties",
      "temporal difference learning",
      "exploration",
      "markov decision process"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}