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. 2007.01612
38
32
v1v2 (latest)

Online learning in MDPs with linear function approximation and bandit feedback

3 July 2020
Gergely Neu
Julia Olkhovskaya
ArXiv (abs)PDFHTML
Abstract

We consider an online learning problem where the learner interacts with a Markov decision process in a sequence of episodes, where the reward function is allowed to change between episodes in an adversarial manner and the learner only gets to observe the rewards associated with its actions. We allow the state space to be arbitrarily large, but we assume that all action-value functions can be represented as linear functions in terms of a known low-dimensional feature map, and that the learner has access to a simulator of the environment that allows generating trajectories from the true MDP dynamics. Our main contribution is developing a computationally efficient algorithm that we call MDP-LinExp3, and prove that its regret is bounded by O~(H2T2/3(dK)1/3)\widetilde{\mathcal{O}}\big(H^2 T^{2/3} (dK)^{1/3}\big)O(H2T2/3(dK)1/3), where TTT is the number of episodes, HHH is the number of steps in each episode, KKK is the number of actions, and ddd is the dimension of the feature map. We also show that the regret can be improved to O~(H2TdK)\widetilde{\mathcal{O}}\big(H^2 \sqrt{TdK}\big)O(H2TdK​) under much stronger assumptions on the MDP dynamics. To our knowledge, MDP-LinExp3 is the first provably efficient algorithm for this problem setting.

View on arXiv
Comments on this paper