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. 2402.11877
30
0

Finite-Time Error Analysis of Online Model-Based Q-Learning with a Relaxed Sampling Model

19 February 2024
Han-Dong Lim
HyeAnn Lee
Donghwan Lee
    OffRL
ArXivPDFHTML
Abstract

Reinforcement learning has witnessed significant advancements, particularly with the emergence of model-based approaches. Among these, QQQ-learning has proven to be a powerful algorithm in model-free settings. However, the extension of QQQ-learning to a model-based framework remains relatively unexplored. In this paper, we delve into the sample complexity of QQQ-learning when integrated with a model-based approach. Through theoretical analyses and empirical evaluations, we seek to elucidate the conditions under which model-based QQQ-learning excels in terms of sample efficiency compared to its model-free counterpart.

View on arXiv
Comments on this paper