用脑电数据间接反馈智能体表现，实现无需主动指令的人机强化学习。
Mapping Neural Signals to Agent Performance, A Step Towards Reinforcement Learning from Neural Feedback
- 通过脑部信号（fNIRS）捕捉人类对智能体行为的隐式反馈。
- 实验证明前额叶皮层信号与智能体性能存在可建模关联。
- 适合研究脑机接口、人机协同与自适应智能系统的人群。
隐式人机强化学习（HITL-RL）在降低人类工作负担的前提下，将被动人类反馈融入自主智能体训练。然而现有方法多依赖主动指令，需参与者以不自然的方式表达意图。本文提出NEURO-LOOP框架，利用人类内在奖励系统驱动人机交互。该研究首次验证了关键步骤：将脑信号映射至智能体表现。基于功能近红外光谱（fNIRS），设计数据集采集参与者观察或引导强化学习智能体时的前额叶皮层信号。采用经典机器学习方法证明，fNIRS数据与智能体性能间存在显著关联。结果表明，神经接口有望推动未来人机协作、辅助型AI及自适应自治系统的发展。
原文摘要 · Abstract (English)
Implicit Human-in-the-Loop Reinforcement Learning (HITL-RL) is a methodology that integrates passive human feedback into autonomous agent training while minimizing human workload. However, existing methods often rely on active instruction, requiring participants to teach an agent through unnatural expression or gesture. We introduce NEURO-LOOP, an implicit feedback framework that utilizes the intrinsic human reward system to drive human-agent interaction. This work demonstrates the feasibility of a critical first step in the NEURO-LOOP framework: mapping brain signals to agent performance. Using functional near-infrared spectroscopy (fNIRS), we design a dataset to enable future research using passive Brain-Computer Interfaces for Human-in-the-Loop Reinforcement Learning. Participants are instructed to observe or guide a reinforcement learning agent in its environment while signals from the prefrontal cortex are collected. We conclude that a relationship between fNIRS data and agent performance exists using classical machine learning techniques. Finally, we highlight the potential that neural interfaces may offer to future applications of human-agent interaction, assistive AI, and adaptive autonomous systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。