REVIEW 1 cited by
Rectangularity and duality of distributionally robust Markov Decision Processes
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The main goal of this paper is to discuss several approaches to formulation of distributionally robust counterparts of Markov Decision Processes, where the transition kernels are not specified exactly but rather are assumed to be elements of the corresponding ambiguity sets. The intent is to clarify some connections between the game and static formulations of distributionally robust MDPs, and delineate the role of rectangularity associated with ambiguity sets in determining these connections.
Forward citations
Cited by 1 Pith paper
-
Risk-averse formulations of Stochastic Optimal Control and Markov Decision Processes
Risk-averse SOC and MDP can be solved by dynamic programming with nested risk functionals, and under a quantile-gap condition the Value-at-Risk sample complexity grows roughly linearly in 1/(1-β).
Discussion (0). Continue with ORCID to comment.