Combining brain-computer interfaces with deep reinforcement learning for robot training: a feasibility study in a simulation environment

This paper looks at deep reinforcement learning (RL) to teach robots how to autonomously learn complex tasks. They compared wet- and dry-based electrode systems as well as the performance of #BCI-based deep RL training vs. feedback given by participants.

New Research: Combining brain-computer interfaces with deep reinforcement learning for robot training: a feasibility study in a simulation environment https://t.co/uPytqVNZWJ #neuroergonomics