Return-conditional diffusion models for policies outperform offline RL on benchmarks by circumventing dynamic programming and enable constraint or skill composition.
Jordan and Joseph E
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
2022 1verdicts
UNVERDICTED 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Is Conditional Generative Modeling all you need for Decision-Making?
Return-conditional diffusion models for policies outperform offline RL on benchmarks by circumventing dynamic programming and enable constraint or skill composition.