PROJECT TITLE :

Neural Control of a Tracking Task via Attention-Gated Reinforcement Learning for Brain-Machine Interfaces

ABSTRACT:

Reinforcement learning (RL)-based mostly brain machine interfaces (BMIs) enable the user to find out from the surroundings through interactions to complete the task without desired signals, that is promising for clinical applications. Previous studies exploited Q-learning techniques to discriminate neural states into simple directional actions providing the trial initial timing. But, the movements in BMI applications will be quite difficult, and therefore the action timing explicitly shows the intention when to move. The wealthy actions and therefore the corresponding neural states form a large state-action space, imposing generalization issue on Q-learning. In this paper, we tend to propose to adopt attention-gated reinforcement learning (AGREL) as a new learning scheme for BMIs to adaptively decode high-dimensional neural activities into seven distinct movements (directional moves, holdings and resting) due to the economical weight-updating. We have a tendency to apply AGREL on neural information recorded from M1 of a monkey to directly predict a seven-action set in a time sequence to reconstruct the trajectory of a center-out task. Compared to Q-learning techniques, AGREL could improve the target acquisition rate to 90.sixteenpercent in average with faster convergence and more stability to follow neural activity over multiple days, indicating the potential to achieve higher on-line decoding performance for additional difficult BMI tasks.