2 papers
cs.RO2020
Maximizing BCI Human Feedback using Active Learning
Zizhao Wang, Junyao Shi, Iretiayo Akinola +1
Recent advancements in \textit{Learning from Human Feedback} present an effective way to train robot agents via inputs from non-expert humans, without a need for a specially design…
cs.RO2019
Accelerated Robot Learning via Human Brain Signals
Iretiayo Akinola, Zizhao Wang, Junyao Shi +6
In reinforcement learning (RL), sparse rewards are a natural way to specify the task to be learned. However, most RL algorithms struggle to learn in this setting since the learning…