Pith. sign in

REVIEW 1 cited by

A PAC Learning Algorithm for LTL and Omega-regular Objectives in 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 2310.12248 v3 pith:UDO7X7YG submitted 2023-10-18 cs.LG cs.LO

classification cs.LGcs.LO
keywords algorithmobjectivesomega-regularlearningintroducemdpsapproximatelyconfirm
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Linear temporal logic (LTL) and omega-regular objectives -- a superset of LTL -- have seen recent use as a way to express non-Markovian objectives in reinforcement learning. We introduce a model-based probably approximately correct (PAC) learning algorithm for omega-regular objectives in Markov decision processes (MDPs). As part of the development of our algorithm, we introduce the epsilon-recurrence time: a measure of the speed at which a policy converges to the satisfaction of the omega-regular objective in the limit. We prove that our algorithm only requires a polynomial number of samples in the relevant parameters, and perform experiments which confirm our theory.

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. Regret-Free Reinforcement Learning for LTL Specifications

    cs.AI 2024-11 conditional novelty 6.0 of 10

    A regret-free (sublinear-regret) episodic algorithm for LTL objectives, built on optimistic interval-MDP value iteration for reach-avoid and a graph-learning preprocess requiring a known minimum transition probability.

Pith tools