Pith. sign in

REVIEW 1 cited by

Metrics and continuity in reinforcement learning

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 2102.01514 v1 pith:UWMCWECC submitted 2021-02-02 cs.LG cs.AIstat.ML

classification cs.LGcs.AIstat.ML
keywords metricslearningreinforcementtopologiesalgorithmsintroduceneighbourhoodssimilarity
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In most practical applications of reinforcement learning, it is untenable to maintain direct estimates for individual states; in continuous-state systems, it is impossible. Instead, researchers often leverage state similarity (whether explicitly or implicitly) to build models that can generalize well from a limited set of samples. The notion of state similarity used, and the neighbourhoods and topologies they induce, is thus of crucial importance, as it will directly affect the performance of the algorithms. Indeed, a number of recent works introduce algorithms assuming the existence of "well-behaved" neighbourhoods, but leave the full specification of such topologies for future work. In this paper we introduce a unified formalism for defining these topologies through the lens of metrics. We establish a hierarchy amongst these metrics and demonstrate their theoretical implications on the Markov Decision Process specifying the reinforcement learning problem. We complement our theoretical results with empirical evaluations showcasing the differences between the metrics considered.

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. Bellman operator convergence enhancements in reinforcement learning algorithms

    cs.LG 2025-05 reject novelty 4.0 of 10

    A new advantage-weighted Bellman operator is claimed to speed up Q-learning convergence, but the proofs are flawed and experiments lack error bars.

Pith tools