{
  "id": 420,
  "url": "https://arxiv.org/abs/2606.31178v1",
  "title": "AETDICE: Unified Framework and Offline Optimization for Nonlinear Multi-Objective RL",
  "summary": "Optimizing nonlinear preferences in multi-objective reinforcement learning (MORL) is essential for capturing complex trade-offs like risk aversion or fairness. However, such non-linearity has historically bifurcated nonlinear MORL objectives into two distinct paradigms: Scalarized Expected Return (SER) and Expected Scalarized Return (ESR). While SER requires global-level optimization and ESR requires non-Markovian policies, leading to fragmented optimization strategies, we bridge this divide thr",
  "authors": "Woosung Kim, Youngjun Suh, Jinho Lee, Jongmin Lee, Byung-Jun Lee",
  "category": "research",
  "topics": "bias-fairness",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-30T06:08:46.000Z",
  "fetched_at": "2026-07-14T14:14:32.646Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/420",
  "original_url": "https://arxiv.org/abs/2606.31178v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}