Doctor is a transformer-based offline RL method that samples candidate actions near a desired return and verifies them with a learned Q-function, improving target-return alignment.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hybrid Sequence Modeling and Reinforced Verification for Controllable Target-Conditioned Decision Making
Doctor is a transformer-based offline RL method that samples candidate actions near a desired return and verifies them with a learned Q-function, improving target-return alignment.