Accelerating Reinforcement Learning via Error-Related Human Brain Signals

TL;DR

This paper demonstrates that error-related EEG signals can be integrated into reinforcement learning to significantly accelerate policy acquisition in complex robotic manipulation tasks, outperforming traditional sparse-reward methods.

Contribution

It introduces a novel framework for incorporating EEG-based neural feedback into reinforcement learning for high-dimensional manipulation tasks, extending prior EEG-guided RL research beyond locomotion.

Findings

Neural feedback accelerates RL in obstacle-rich manipulation environments.

Optimal human-feedback weighting improves task success rates.

Framework remains robust across different subjects despite EEG variability.

Abstract

In this work, we investigate how implicit neural feed back can accelerate reinforcement learning in complex robotic manipulation settings. While prior electroencephalogram (EEG) guided reinforcement learning studies have primarily focused on navigation or low-dimensional locomotion tasks, we aim to understand whether such neural evaluative signals can improve policy learning in high-dimensional manipulation tasks involving obstacles and precise end-effector control. We integrate error related potentials decoded from offline-trained EEG classifiers into reward shaping and systematically evaluate the impact of human-feedback weighting. Experiments on a 7-DoF manipulator in an obstacle-rich reaching environment show that neural feedback accelerates reinforcement learning and, depending on the human-feedback weighting, can yield task success rates that at times exceed those of sparse-reward baselines. Moreover, when applying the best-performing feedback weighting across all sub jects, we observe consistent acceleration of reinforcement learning relative to the sparse-reward setting. Furthermore, leave-one subject-out evaluations confirm that the proposed framework remains robust despite the intrinsic inter-individual variability in EEG decodability. Our findings demonstrate that EEG-based reinforcement learning can scale beyond locomotion tasks and provide a viable pathway for human-aligned manipulation skill acquisition.