Pith. sign in

REVIEW 1 cited by

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

arxiv 2307.15890 v1 pith:MHIFF3OI submitted 2023-07-29 math.OC cs.LG

First-order Policy Optimization for Robust Policy Evaluation

classification math.OC cs.LG
keywords policyrobustevaluationmathrmoptimizationstochasticambiguitydeterministic
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We adopt a policy optimization viewpoint towards policy evaluation for robust Markov decision process with $\mathrm{s}$-rectangular ambiguity sets. The developed method, named first-order policy evaluation (FRPE), provides the first unified framework for robust policy evaluation in both deterministic (offline) and stochastic (online) settings, with either tabular representation or generic function approximation. In particular, we establish linear convergence in the deterministic setting, and $\tilde{\mathcal{O}}(1/\epsilon^2)$ sample complexity in the stochastic setting. FRPE also extends naturally to evaluating the robust state-action value function with $(\mathrm{s}, \mathrm{a})$-rectangular ambiguity sets. We discuss the application of the developed results for stochastic policy optimization of large-scale robust MDPs.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Robust Markov Decision Processes on Continuous State Spaces

    math.OC 2026-05 unverdicted novelty 6.0

    Develops stochastic first-order methods for robust policy evaluation and approximate policy iteration in continuous-state robust MDPs, achieving 'O(1/ε^{2}) sample complexity for both evaluation and optimization.