Healthy-to-Stroke Translation of EEG-Based BMIs: EEG Characterization and Reinforcement Learning-Based Decoder Evaluation
Zander Via, Ava M. Kruse, Bhoj Raj Thapa, Jihye Bae
This paper evaluates whether population-trained Q-learning Kernel Temporal Difference (Q-KTD) decoders can improve individual stroke decoding through healthy-to-stroke transfer learning.
bioRxiv · Jun 29, 2026 · PreprintBioengineering