R2CSL provably reaches the in-distribution optimal stitched policy by conditioning on the maximum return-to-go per state, improving on standard RCSL without dynamic programming.
Generalized decision transformer for of- fline hindsight information matching
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
-
How to Provably Improve Return Conditioned Supervised Learning?
R2CSL provably reaches the in-distribution optimal stitched policy by conditioning on the maximum return-to-go per state, improving on standard RCSL without dynamic programming.