Pith. sign in

REVIEW 1 cited by

On Dynamic Programming Decompositions of Static Risk Measures in 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

arxiv 2304.12477 v4 pith:ARYSDNFA submitted 2023-04-24 math.OC cs.AI

classification math.OCcs.AI
keywords decompositionsriskdynamicprogrammingalgorithmsbecausecvardecision
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Optimizing static risk-averse objectives in Markov decision processes is difficult because they do not admit standard dynamic programming equations common in Reinforcement Learning (RL) algorithms. Dynamic programming decompositions that augment the state space with discrete risk levels have recently gained popularity in the RL community. Prior work has shown that these decompositions are optimal when the risk level is discretized sufficiently. However, we show that these popular decompositions for Conditional-Value-at-Risk (CVaR) and Entropic-Value-at-Risk (EVaR) are inherently suboptimal regardless of the discretization level. In particular, we show that a saddle point property assumed to hold in prior literature may be violated. However, a decomposition does hold for Value-at-Risk and our proof demonstrates how this risk measure differs from CVaR and EVaR. Our findings are significant because risk-averse algorithms are used in high-stake environments, making their correctness much more critical.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Computing Monetary Risk Measures in Linear Time

    cs.LG 2026-07 accept novelty 6.0 of 10

    QuickVaR and QuickDivergence compute VaR and EWS φ-divergence risk measures (CVaR, TVaR) in expected O(n) time by avoiding full sorts via Quickselect-style partitioning and polymatroid structure.

Pith tools