Offline-to-online value adaptation in RL has a minimax lower bound matching pure online learning in hard cases, yet O2O-LSVI improves sample complexity under a novel structural condition on pretrained Q-functions.
Simon S Du, Sham M Kakade, Ruosong Wang, and Lin F Yang
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Category theory proves prompt-based learning on perfect foundation models works only for representable tasks, fine-tuning solves tasks in the pretext category, and models can represent unseen target-category objects using source-category structure.
citing papers explorer
-
Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation
Offline-to-online value adaptation in RL has a minimax lower bound matching pure online learning in hard cases, yet O2O-LSVI improves sample complexity under a novel structural condition on pretrained Q-functions.
-
On the Power of Foundation Models
Category theory proves prompt-based learning on perfect foundation models works only for representable tasks, fine-tuning solves tasks in the pretext category, and models can represent unseen target-category objects using source-category structure.