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. 2410.13772
51
3
v1v2 (latest)

Is Prior-Free Black-Box Non-Stationary Reinforcement Learning Feasible?

17 October 2024
Argyrios Gerogiannis
Yu-Han Huang
Venugopal V. Veeravalli
ArXiv (abs)PDFHTML
Abstract

We study the problem of Non-Stationary Reinforcement Learning (NS-RL) without prior knowledge about the system's non-stationarity. A state-of-the-art, black-box algorithm, known as MASTER, is considered, with a focus on identifying the conditions under which it can achieve its stated goals. Specifically, we prove that MASTER's non-stationarity detection mechanism is not triggered for practical choices of horizon, leading to performance akin to a random restarting algorithm. Moreover, we show that the regret bound for MASTER, while being order optimal, stays above the worst-case linear regret until unreasonably large values of the horizon. To validate these observations, MASTER is tested for the special case of piecewise stationary multi-armed bandits, along with methods that employ random restarting, and others that use quickest change detection to restart. A simple, order optimal random restarting algorithm, that has prior knowledge of the non-stationarity is proposed as a baseline. The behavior of the MASTER algorithm is validated in simulations, and it is shown that methods employing quickest change detection are more robust and consistently outperform MASTER and other random restarting approaches.

View on arXiv
@article{gerogiannis2025_2410.13772,
  title={ Is Prior-Free Black-Box Non-Stationary Reinforcement Learning Feasible? },
  author={ Argyrios Gerogiannis and Yu-Han Huang and Venugopal V. Veeravalli },
  journal={arXiv preprint arXiv:2410.13772},
  year={ 2025 }
}
Comments on this paper