ORAC combines upper-confidence-bound reward exploration with lower-confidence-bound risk-averse cost constraints and adaptive cost weighting to improve exploration in risk-averse constrained RL.
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
-
Optimistic Exploration for Risk-Averse Constrained Reinforcement Learning
ORAC combines upper-confidence-bound reward exploration with lower-confidence-bound risk-averse cost constraints and adaptive cost weighting to improve exploration in risk-averse constrained RL.