AI Research

Redistribution-based Cost Inference Improves Sparse Safe Offline RL

Medium Severity Global
Date Occurred Aug 12, 2026 17:53 UTC
Event Type AI Research
Source arXiv
Recorded Aug 13, 2026
Full Description

arXiv: Redistribution-based Cost Inference Improves Sparse Safe Offline RL Safe offline RL typically assumes access to dense per-step cost annotations, but in practice supervisors provide only trajectory-level stop-feedback: a binary signal at the first unsafe transition, with no per-step attribution. We frame this as a temporal credit assignment problem and propose the Redistribution-based Cost Inference (RCI) framework, which converts sparse stop-feedback into dense per-step costs via return decomposition, then trains a constrained offline policy on the augmented dat

AI Intelligence Layer

AI Categories

ethics
Event Metadata
  • ID #23348
  • Type AI Research
  • Region Global
  • Severity Medium
  • Indexed Aug 13, 2026