{
  "id": "1802.07668",
  "version": "v1",
  "published": "2018-02-21T17:07:06.000Z",
  "updated": "2018-02-21T17:07:06.000Z",
  "title": "A model for system uncertainty in reinforcement learning",
  "authors": [
    "Ryan Murray",
    "Michele Palladino"
  ],
  "categories": [
    "math.OC"
  ],
  "abstract": "This work provides a rigorous framework for studying continuous time control problems in uncertain environments. The framework considered models uncertainty in state dynamics as a measure on the space of functions. This measure is considered to change over time as agents learn their environment. This model can be seem as a variant of either Bayesian reinforcement learning or adaptive control. We study necessary conditions for locally optimal trajectories within this model, in particular deriving an appropriate dynamic programming principle and Hamilton-Jacobi equations. This model provides one possible framework for studying the tradeoff between exploration and exploitation in reinforcement learning.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-02-21T17:07:06.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "reinforcement learning",
      "system uncertainty",
      "studying continuous time control problems",
      "appropriate dynamic programming principle",
      "study necessary conditions"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}