RAD retrieves high-return states from an offline dataset and uses condition-guided diffusion to plan toward them, reporting competitive D4RL MuJoCo scores.
Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor
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.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
RAD: Retrieval High-quality Demonstrations to Enhance Decision-making
RAD retrieves high-return states from an offline dataset and uses condition-guided diffusion to plan toward them, reporting competitive D4RL MuJoCo scores.