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

arXiv: https://arxiv.org/abs/2410.13772 · HTML: https://mlsanity.com/paper/2410.13772/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods.
- First posted on arXiv 17 Oct 2024.

## Placed in

- Deep reinforcement learning methods / [RL theory and sample complexity](https://mlsanity.com/deeprl/rl-theory-and-sample-complexity/)

## Built on by (most cited first, 5 of 5)

- [Non-Stationary Lipschitz Bandits](https://mlsanity.com/paper/2505.18871/) (2025)
- [Detection Augmented Bandit Procedures for Piecewise Stationary MABs: A Modular Approach](https://mlsanity.com/paper/2501.01291/) (2025)
- [DAL: A Practical Prior-Free Black-Box Framework for Piecewise Stationary Bandits](https://mlsanity.com/paper/2501.19401/) (2025)
- [DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees](https://mlsanity.com/paper/2604.16684/) (2026)
- [Nonstationary Generalized Linear Bandits with Discounted Online Mirror Descent](https://mlsanity.com/paper/2605.25590/) (2026)

## Abstract (arXiv)

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.