A plug-in that retrieves expert actions from a small associative memory buffer improves offline Decision Transformer performance on three of four D4RL MuJoCo tasks, with gains up to 10.7 points.
Offline reinforcement learning as one big sequence modeling problem
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
-
Re:Frame -- Retrieving Experience From Associative Memory
A plug-in that retrieves expert actions from a small associative memory buffer improves offline Decision Transformer performance on three of four D4RL MuJoCo tasks, with gains up to 10.7 points.