Worst-case sampling, defined as initial states on the safety envelope boundary, makes physics-regulated deep RL train safer policies with fewer episodes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Physics-model-guided Worst-case Sampling for Safe Reinforcement Learning
Worst-case sampling, defined as initial states on the safety envelope boundary, makes physics-regulated deep RL train safer policies with fewer episodes.