Pith. sign in

REVIEW 1 cited by

Truly No-Regret Learning in Constrained MDPs

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 2402.15776 v3 pith:ZQ7QCQ3S submitted 2024-02-24 cs.LG stat.ML

classification cs.LGstat.ML
keywords learningprimal-dualalgorithmscancellationscmdpserrorregretalgorithm
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Constrained Markov decision processes (CMDPs) are a common way to model safety constraints in reinforcement learning. State-of-the-art methods for efficiently solving CMDPs are based on primal-dual algorithms. For these algorithms, all currently known regret bounds allow for error cancellations -- one can compensate for a constraint violation in one round with a strict constraint satisfaction in another. This makes the online learning process unsafe since it only guarantees safety for the final (mixture) policy but not during learning. As Efroni et al. (2020) pointed out, it is an open question whether primal-dual algorithms can provably achieve sublinear regret if we do not allow error cancellations. In this paper, we give the first affirmative answer. We first generalize a result on last-iterate convergence of regularized primal-dual schemes to CMDPs with multiple constraints. Building upon this insight, we propose a model-based primal-dual algorithm to learn in an unknown CMDP. We prove that our algorithm achieves sublinear regret without error cancellations.

Discussion (0). Continue with ORCID 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. An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints

    cs.LG 2025-05 reject novelty 5.0 of 10

    A primal-dual algorithm with optimistic mirror descent is claimed to achieve O~(sqrt K) regret and O~(sqrt K) strong constraint violation in episodic CMDPs with anytime adversarial constraints, without Slater's condition.

Pith tools