English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Providing Reinforcement Learning (RL) agents with human feedback candramatically improve various aspects of learning. However, previous methodsrequire human observer to give inputs explicitly (e.g., press buttons, voiceinterface), burdening the human in the loop of RL agent's learning process.Further, it is sometimes difficult or impossible to obtain the explicit humanadvise (feedback), e.g., autonomous driving, disabled rehabilitation, etc. Inthis work, we investigate capturing human's intrinsic reactions as implicit(and natural) feedback through EEG in the form of error-related potentials(ErrP), providing a natural and direct way for humans to improve the RL agentlearning. As such, the human intelligence can be integrated via implicitfeedback with RL algorithms to accelerate the learning of RL agent. We developthree reasonably complex 2D discrete navigational games to experimentallyevaluate the overall performance of the proposed work. Major contributions ofour work are as follows,  (i) we propose and experimentally validate the zero-shot learning of ErrPs,where the ErrPs can be learned for one game, and transferred to other unseengames, (ii) we propose a novel RL framework for integrating implicit humanfeedbacks via ErrPs with RL agent, improving the label efficiency androbustness to human mistakes, and (iii) compared to prior works, we scale theapplication of ErrPs to reasonably complex environments, and demonstrate thesignificance of our approach for accelerated learning through real userexperiments.

Accelerating Reinforcement Learning Agent with EEG-based Implicit Human Feedback