Presents the first algorithm to identify an ε-optimal policy in robust constrained MDPs via epigraph form and bisection search with Õ(ε^{-4}) robust policy evaluations.
Learning with Safety Constraints: Sample Complexity of Reinforcement Learning for Constrained MDPs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form
Presents the first algorithm to identify an ε-optimal policy in robust constrained MDPs via epigraph form and bisection search with Õ(ε^{-4}) robust policy evaluations.