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. 1808.01813
17
46

Regret Bounds for Reinforcement Learning via Markov Chain Concentration

6 August 2018
R. Ortner
ArXivPDFHTML
Abstract

We give a simple optimistic algorithm for which it is easy to derive regret bounds of O~(tmixSAT)\tilde{O}(\sqrt{t_{\rm mix} SAT})O~(tmix​SAT​) after TTT steps in uniformly ergodic Markov decision processes with SSS states, AAA actions, and mixing time parameter tmixt_{\rm mix}tmix​. These bounds are the first regret bounds in the general, non-episodic setting with an optimal dependence on all given parameters. They could only be improved by using an alternative mixing time parameter.

View on arXiv
Comments on this paper