ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2302.06834
13
12

Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization

14 February 2023
Fang-yuan Kong
Xiangcheng Zhang
Baoxiang Wang
Shuai Li
ArXivPDFHTML
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 O~(K6/7)\tilde{O}(K^{6/7})O~(K6/7) (KKK 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 O~(K4/5)\tilde{O}(K^{4/5})O~(K4/5) 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.

View on arXiv
Comments on this paper