Pith. sign in

REVIEW 2 cited by

The Plug-in Approach for Average-Reward and Discounted MDPs: Optimal Sample Complexity Analysis

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 2410.07616 v2 pith:QPK7FTAV submitted 2024-10-10 cs.LG cs.ITmath.ITmath.OCstat.ML

classification cs.LGcs.ITmath.ITmath.OCstat.ML
keywords approachplug-inoptimalsampleaverage-rewardboundscomplexitydiscounted
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

We study the sample complexity of the plug-in approach for learning $\varepsilon$-optimal policies in average-reward Markov decision processes (MDPs) with a generative model. The plug-in approach constructs a model estimate then computes an average-reward optimal policy in the estimated model. Despite representing arguably the simplest algorithm for this problem, the plug-in approach has never been theoretically analyzed. Unlike the more well-studied discounted MDP reduction method, the plug-in approach requires no prior problem information or parameter tuning. Our results fill this gap and address the limitations of prior approaches, as we show that the plug-in approach is optimal in several well-studied settings without using prior knowledge. Specifically it achieves the optimal diameter- and mixing-based sample complexities of $\widetilde{O}\left(SA \frac{D}{\varepsilon^2}\right)$ and $\widetilde{O}\left(SA \frac{\tau_{\mathrm{unif}}}{\varepsilon^2}\right)$, respectively, without knowledge of the diameter $D$ or uniform mixing time $\tau_{\mathrm{unif}}$. We also obtain span-based bounds for the plug-in approach, and complement them with algorithm-specific lower bounds suggesting that they are unimprovable. Our results require novel techniques for analyzing long-horizon problems which may be broadly useful and which also improve results for the discounted plug-in approach, removing effective-horizon-related sample size restrictions and obtaining the first optimal complexity bounds for the full range of sample sizes without reward perturbation.

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. Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis

    cs.LG 2025-05 reject novelty 7.0 of 10

    RHI is claimed to find an epsilon-optimal robust policy under the average-reward criterion with about SAH^2/epsilon^2 samples under the communicating assumption, with a parameter-free variant that avoids knowing H.

  2. Statistical and Algorithmic Foundations of Reinforcement Learning

    stat.ML 2025-07 accept

    A tutorial collecting minimax sample complexity results for tabular RL across generative model, online, offline, robust, and human-feedback settings.

Pith tools