A liveness-based Bellman operator enables conservative offline policy evaluation for manipulation tasks by encoding task progression and reducing truncation bias from finite horizons.
Dif- fusion policy: Visuomotor policy learning via action diffusion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Offline Policy Evaluation for Manipulation Policies via Discounted Liveness Formulation
A liveness-based Bellman operator enables conservative offline policy evaluation for manipulation tasks by encoding task progression and reducing truncation bias from finite horizons.