An offline imitation method that assigns each demonstration a learned style code and blends similar codes can reproduce varied behaviors and allow a user to select the behavior.
Decision transformer: Reinforcement learning via sequence modeling, 2021
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
-
Offline Learning of Controllable Diverse Behaviors
An offline imitation method that assigns each demonstration a learned style code and blends similar codes can reproduce varied behaviors and allow a user to select the behavior.