PLS combines offline return-conditioned policy training with Gaussian-process safe optimization of target returns to provide high-probability safety throughout deployment.
Title resolution pending
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
-
A Provable Approach for End-to-End Safe Reinforcement Learning
PLS combines offline return-conditioned policy training with Gaussian-process safe optimization of target returns to provide high-probability safety throughout deployment.