Pith. sign in

REVIEW 1 cited by

Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization

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 2302.06834 v1 pith:N6CLX3TT submitted 2023-02-14 cs.LG cs.AI

Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization

classification cs.LG cs.AI
keywords linearadversarialoptimizationproblemchallengingenvironmentfunctionimproved
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Learning Markov decision processes (MDP) in an adversarial environment has been a challenging problem. The problem becomes even more challenging with function approximation, since the underlying structure of the loss function and transition kernel are especially hard to estimate in a varying environment. In fact, the state-of-the-art results for linear adversarial MDP achieve a regret of $\tilde{O}(K^{6/7})$ ($K$ denotes the number of episodes), which admits a large room for improvement. In this paper, we investigate the problem with a new view, which reduces linear MDP into linear optimization by subtly setting the feature maps of the bandit arms of linear optimization. This new technique, under an exploratory assumption, yields an improved bound of $\tilde{O}(K^{4/5})$ for linear adversarial MDP without access to a transition simulator. The new view could be of independent interest for solving other MDP problems that possess a linear structure.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. World Action Planner: Generalizable Decision-Making with Action-Conditioned World Models

    cs.AI 2026-07 conditional novelty 6.0

    Pairing VLM-generated action proposals with rollouts from a pose-image-conditioned video world model yields high success rates in novel simulated manipulation tasks without end-to-end policy retraining.