6 papers
DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees
Argyrios Gerogiannis, Yu-Han Huang, Venugopal V. Veeravalli
We study model-free reinforcement learning (RL) in non-stationary finite-horizon episodic Markov decision processes (MDPs) without prior knowledge of the non-stationarity. We focus…
Learning Where to Look: UCB-Driven Controlled Sensing for Quickest Change Detection
Yu-Han Huang, Argyrios Gerogiannis, Subhonmesh Bose +1
We study the multichannel quickest change detection problem with bandit feedback and controlled sensing, in which an agent sequentially selects one of the data streams to observe a…
Finite-Horizon Quickest Change Detection Balancing Latency with False Alarm Probability
Yu-Han Huang, Venugopal V. Veeravalli
A finite-horizon variant of the quickest change detection (QCD) problem that is of relevance to learning in non-stationary environments is studied. The metric characterizing false…
Detection Augmented Bandit Procedures for Piecewise Stationary MABs: A Modular Approach
Yu-Han Huang, Argyrios Gerogiannis, Subhonmesh Bose +1
Conventional Multi-Armed Bandit (MAB) algorithms are designed for stationary environments, where the reward distributions associated with the arms do not change with time. In many…
Sequential Change Detection for Learning in Piecewise Stationary Bandit Environments
Yu-Han Huang, Venugopal V. Veeravalli
A finite-horizon variant of the quickest change detection problem is investigated, which is motivated by a change detection problem that arises in piecewise stationary bandits. The…
Is Prior-Free Black-Box Non-Stationary Reinforcement Learning Feasible?
Argyrios Gerogiannis, Yu-Han Huang, Venugopal V. Veeravalli
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…