{
  "id": 4430,
  "url": "https://arxiv.org/abs/2605.12771v1",
  "title": "Adaptive Smooth Tchebycheff Attention for Multi-Objective Policy Optimization",
  "summary": "Multi-objective reinforcement learning in robotic domains requires balancing complex, non-convex trade-offs between conflicting objectives. While linear scalarization methods provide stability, they are theoretically incapable of recovering solutions within non-convex regions of the Pareto front. Conversely, static non-linear scalarizations (e.g., Tchebycheff) can theoretically access these regions but often suffer from severe gradient variance and optimization instability in deep RL. In this wo",
  "authors": "Alejandro Murillo-Gonzalez, Mahmoud Ali, Lantao Liu",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-12T21:32:57.000Z",
  "fetched_at": "2026-07-14T16:30:59.237Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4430",
  "original_url": "https://arxiv.org/abs/2605.12771v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}