Pith. sign in

REVIEW 2 cited by

An Efficient Solution to s-Rectangular 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

arxiv 2301.13642 v1 pith:4MHLZH5H submitted 2023-01-31 cs.LG math.OC

classification cs.LGmath.OC
keywords robustdecisionefficientmarkovmdpsoptimalpoliciesprocesses
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We present an efficient robust value iteration for \texttt{s}-rectangular robust Markov Decision Processes (MDPs) with a time complexity comparable to standard (non-robust) MDPs which is significantly faster than any existing method. We do so by deriving the optimal robust Bellman operator in concrete forms using our $L_p$ water filling lemma. We unveil the exact form of the optimal policies, which turn out to be novel threshold policies with the probability of playing an action proportional to its advantage.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Distributionally Robust Deep Q-Learning

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Sinkhorn-ball robust Bellman equation for continuous-state MDPs is implemented as a Robust DQN that learns policies robust to transition-model misspecification.

  2. Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A pessimism-based framework for zero-shot transfer RL builds conservative proxies from robust MDPs, yielding lower-bound performance guarantees and distributed algorithms that mitigate negative transfer.

Pith tools