RHC-UCRL is the first algorithm for safety-constrained RL under explicit adversarial dynamics, providing sub-linear regret and constraint violation guarantees by maintaining optimism over both agent and adversary policies.
Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
Introduces a graded safety framework for emergency landing flight envelopes using state- and time-dependent violation cost functions in Hamilton-Jacobi reachability, with monotonicity properties and a convergent synthesis algorithm for least conservative parameters.
RMDPs lack subgradient dominance in general and admit suboptimal local minima; finding epsilon-optimal policies is NP-hard for finite transition uncertainty sets, but the dominance property holds when worst-case kernels or action-values are unique per policy.
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.
A sound and optimal shielding method for robust MDPs ensures LTL safety under worst-case transitions and combines with PAC sampling to produce minimally restrictive shields for learned models.
citing papers explorer
-
Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees
RHC-UCRL is the first algorithm for safety-constrained RL under explicit adversarial dynamics, providing sub-linear regret and constraint violation guarantees by maintaining optimism over both agent and adversary policies.
-
Characterization and Analysis of Emergency Landing Flight Envelopes with Graded Safety Specifications
Introduces a graded safety framework for emergency landing flight envelopes using state- and time-dependent violation cost functions in Hamilton-Jacobi reachability, with monotonicity properties and a convergent synthesis algorithm for least conservative parameters.
-
Revisiting Subgradient Dominance in Robust MDPs: Counterexamples, Hardness, and Sufficient Conditions
RMDPs lack subgradient dominance in general and admit suboptimal local minima; finding epsilon-optimal policies is NP-hard for finite transition uncertainty sets, but the dominance property holds when worst-case kernels or action-values are unique per policy.
-
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.
-
Robust Shielding for Safe Reinforcement Learning
A sound and optimal shielding method for robust MDPs ensures LTL safety under worst-case transitions and combines with PAC sampling to produce minimally restrictive shields for learned models.