GCReinSL adds Q-conditioned maximization to supervised offline RL, using normalizing flows to estimate goal-reaching probabilities and expectile regression to condition actions on the best in-distribution value, improving trajectory stitching.
When does return-conditioned supervised learning work for offline reinforcement learning? Advances in Neural Information Processing Systems, 35: 0 1542--1553, 2022
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.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Closing the Gap between TD Learning and Supervised Learning with $Q$-Conditioned Maximization
GCReinSL adds Q-conditioned maximization to supervised offline RL, using normalizing flows to estimate goal-reaching probabilities and expectile regression to condition actions on the best in-distribution value, improving trajectory stitching.