{
  "annotation_id": "27690b7f-19e0-4a06-b544-f4fd7b06ece8",
  "date_created": "2026-02-17T05:53:16.294000Z",
  "date_modified": "2026-02-17T05:53:16.294000Z",
  "file_hash": "5f545eed150024393ee875238bb961c9dfaea8e1e1aa87245cc30a53aa025048",
  "private": false,
  "record": {
    "abstract": "We unify Hamilton-Jacobi (HJ) reachability and Reinforcement Learning (RL) through a proposed running cost formulation. We prove that the resultant travel-cost value function is the unique bounded viscosity solution of a time-dependent Hamilton-Jacobi Bellman (HJB) Partial Differential Equation (PDE) with zero terminal data, whose negative sublevel set equals the strict backward-reachable tube. Using a forward reparameterization and a contraction inducing Bellman update, we show that fixed points of small-step RL value iteration converge to the viscosity solution of the forward discounted HJB. Experiments on a classical benchmark compare learned values to semi-Lagrangian HJB ground truth and quantify error.",
    "arxiv_id": "2601.08050",
    "authors": [
      "Prashant Solanki",
      "Isabelle El-Hajj",
      "Jasper van Beers",
      "Erik-Jan van Kampen",
      "Coen de Visser"
    ],
    "categories": [
      "eess.SY",
      "cs.SY"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "title": "Formalizing the Relationship between Hamilton-Jacobi Reachability and Reinforcement Learning",
    "url": "https://arxiv.org/abs/2601.08050",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "9ce1f93c-6637-463d-9f2d-9956f4e51cb4",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}