Redistribution-based Cost Inference Improves Sparse Safe Offline RL

By Ebenezer Gelo · Paper · cs.LG

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 proble

Cs.lg

View original

HomeResourceLoading…