activity
20062026
most citedReinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration

27 citations · 108 across the 34 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.LG2026

ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policies

Tzu-Hsiang Lin, Srinivas Shakkottai, Dileep Kalathil +1

Behavior-cloned diffusion policies are expressive but remain vulnerable to covariate shift: small deviations from demonstrated states can compound into task failure. Existing metho…