Pith. sign in

REVIEW 1 cited by

Pessimistic Nonlinear Least-Squares Value Iteration for Offline 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 2310.01380 v2 pith:NGTNLBIY submitted 2023-10-02 cs.LG math.OCstat.ML

classification cs.LGmath.OCstat.ML
keywords functionofflineapproximationinstance-dependentiterationlinearnon-linearoptimal
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Offline reinforcement learning (RL), where the agent aims to learn the optimal policy based on the data collected by a behavior policy, has attracted increasing attention in recent years. While offline RL with linear function approximation has been extensively studied with optimal results achieved under certain assumptions, many works shift their interest to offline RL with non-linear function approximation. However, limited works on offline RL with non-linear function approximation have instance-dependent regret guarantees. In this paper, we propose an oracle-efficient algorithm, dubbed Pessimistic Nonlinear Least-Square Value Iteration (PNLSVI), for offline RL with non-linear function approximation. Our algorithmic design comprises three innovative components: (1) a variance-based weighted regression scheme that can be applied to a wide range of function classes, (2) a subroutine for variance estimation, and (3) a planning phase that utilizes a pessimistic value iteration approach. Our algorithm enjoys a regret bound that has a tight dependency on the function class complexity and achieves minimax optimal instance-dependent regret when specialized to linear function approximation. Our work extends the previous instance-dependent results within simpler function classes, such as linear and differentiable function to a more general framework.

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. On the Statistical Complexity for Offline and Low-Adaptive Reinforcement Learning with Structures

    cs.LG 2025-01 conditional

    A review of tight statistical bounds for offline policy evaluation, offline policy learning, and low-adaptive exploration in tabular, linear, and parametric MDPs.

Pith tools