Reinforcement Learning in Reproducing Kernel Hilbert Spaces

This tutorial reviews a series of reinforcement learning (RL) methods implemented in a reproducing kernel Hilbert space (RKHS) developed to address the challenges imposed on decoder design. RL-based decoders enable the user to learn the prosthesis control through interactions without desired signals and better represent the subject’s goal to complete the task. The numerous actions in complex tasks and nonstationary neural states form a vast and dynamic state–action space, imposing a computational challenge in the decoder to detect the emerging neural patterns as well as quickly establish and adjust the globally optimal policy.