CROP adds a conservative reward objective to model-based offline policy optimization that jointly reduces estimation error and random-action rewards to produce robust conservative estimates and mitigate distribution shift.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CROP: Conservative Reward for Model-based Offline Policy Optimization
CROP adds a conservative reward objective to model-based offline policy optimization that jointly reduces estimation error and random-action rewards to produce robust conservative estimates and mitigate distribution shift.