{
  "id": 14495,
  "url": "https://arxiv.org/abs/2607.23617v1",
  "title": "Optimal Reward Shaping: Autonomous Car Parking Case Study",
  "summary": "Designing effective reward functions for model-free reinforcement learning under non-holonomic constraints remains a persistent challenge, often resulting in severe local minima such as policy paralysis or over-conservative hazard avoidance. In this work, we present a parameterized reward shaping framework featuring coverage-gated alignment feedback, drive-direction switch regularization, and an aligned episode termination mechanism evaluated on an autonomous parallel parking task. Crucially, we",
  "authors": "Emre Özkaya, Nicolas R. Gauger",
  "category": "research",
  "topics": "regulation,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-26T11:49:23.000Z",
  "fetched_at": "2026-07-29T05:10:12.205Z",
  "source_slug": "arxiv-cslg",
  "source_name": "arXiv cs.LG",
  "source_homepage": "https://arxiv.org/list/cs.LG/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/14495",
  "original_url": "https://arxiv.org/abs/2607.23617v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}