{
  "id": "1811.04471",
  "version": "v1",
  "published": "2018-11-11T20:17:01.000Z",
  "updated": "2018-11-11T20:17:01.000Z",
  "title": "Thompson Sampling for Pursuit-Evasion Problems",
  "authors": [
    "Zhen Li",
    "Nicholas J. Meyer",
    "Eric B. Laber",
    "Robert Brigantic"
  ],
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "Pursuit-evasion is a multi-agent sequential decision problem wherein a group of agents known as pursuers coordinate their traversal of a spatial domain to locate an agent trying to evade them. Pursuit evasion problems arise in a number of import application domains including defense and route planning. Learning to optimally coordinate pursuer behaviors so as to minimize time to capture of the evader is challenging because of a large action space and sparse noisy state information; consequently, previous approaches have relied primarily on heuristics. We propose a variant of Thompson Sampling for pursuit-evasion that allows for the application of existing model-based planning algorithms. This approach is general in that it allows for an arbitrary number of pursuers, a general spatial domain, and the integration of auxiliary information provided by informants. In a suite of simulation experiments, Thompson Sampling for pursuit evasion significantly reduces time-to-capture relative to competing algorithms.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-11-11T20:17:01.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "thompson sampling",
      "pursuit-evasion problems",
      "significantly reduces time-to-capture relative",
      "multi-agent sequential decision problem",
      "spatial domain"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}