Extracting task vectors from offline data to define training task distributions improves zero-shot offline RL performance by an average of 20%.
Title resolution pending
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.AI 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Improving Zero-Shot Offline RL via Behavioral Task Sampling
Extracting task vectors from offline data to define training task distributions improves zero-shot offline RL performance by an average of 20%.