Augmenting model-based RL agents with calibrated predictive uncertainties improves planning, sample efficiency, and exploration on continuous control tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Calibrated Model-Based Deep Reinforcement Learning
Augmenting model-based RL agents with calibrated predictive uncertainties improves planning, sample efficiency, and exploration on continuous control tasks.