{
  "id": 12271,
  "url": "https://arxiv.org/abs/2607.16999v1",
  "title": "Counterfactual Shapley Credit Assignment",
  "summary": "The Credit Assignment Problem (CAP) is fundamental to developing efficient and explainable Reinforcement Learning (RL) agents. Existing frameworks, whether relying on temporal contiguity or hindsight-conditioned reward reweighting, frequently fail to attribute properly between an agent's policy (skill) and environmental stochasticity (luck). A principled approach to CAP must isolate the true causal drivers of observed outcomes from spurious correlations and environmental randomness. We introduce",
  "authors": "Mingxuan Li, Kaizhan-Lee, Elias Bareinboim",
  "category": "research",
  "topics": "regulation,agents-autonomy,transparency,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-18T23:28:20.000Z",
  "fetched_at": "2026-07-21T05:10:12.656Z",
  "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/12271",
  "original_url": "https://arxiv.org/abs/2607.16999v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}