Scholarlink

<p>Brain-inspired reinforcement learning is pivotal for artificial general intelligence, yet current artificial neural network-based hardware lacks critical biological mechanisms like third-terminal modulated eligibility traces and dynamic reward signaling. Emerging materials address these challenges by efficiently mimicking complex reinforcement learning dynamics. Here, we demonstrate a brain-inspired spiking neural network-based reinforcement learning computing architecture using α-In<sub>2</sub>Se<sub>3</sub> ferroelectric semiconductor field-effect transistor. By leveraging the intrinsic in-plane and out-of-plane polarization coupling of α-In<sub>2</sub>Se<sub>3</sub>, the multi-terminal conductance modulation in the device enables reward signal modulation of reinforcement learning. The ferroelectric relaxation is utilized to implement biological eligibility trace decay, thereby enhancing the algorithm’s processing capability. autonomous driving tasks are then demonstrated with an RL neural network constructed by the α-In<sub>2</sub>Se<sub>3</sub> transistor array, where in-situ reward-based weight updates and eligibility trace decay are performed without any external memory or computing units. Our solution enables a fully functional, energy-efficient, and low-overhead spiking-based reinforcement learning architecture.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Brain-inspired synaptic transistors for in-situ spiking reinforcement learning with eligibility trace

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月21日

查看全文
  • Yasai Wang,
  • Weiwei Xiong,
  • Jianmin Yan,
  • Yue Zhou,
  • Chaoyi Zhu,
  • Xiangshui Miao,
  • Yuhui He,
  • Yang Chai

摘要

Brain-inspired reinforcement learning is pivotal for artificial general intelligence, yet current artificial neural network-based hardware lacks critical biological mechanisms like third-terminal modulated eligibility traces and dynamic reward signaling. Emerging materials address these challenges by efficiently mimicking complex reinforcement learning dynamics. Here, we demonstrate a brain-inspired spiking neural network-based reinforcement learning computing architecture using α-In2Se3 ferroelectric semiconductor field-effect transistor. By leveraging the intrinsic in-plane and out-of-plane polarization coupling of α-In2Se3, the multi-terminal conductance modulation in the device enables reward signal modulation of reinforcement learning. The ferroelectric relaxation is utilized to implement biological eligibility trace decay, thereby enhancing the algorithm’s processing capability. autonomous driving tasks are then demonstrated with an RL neural network constructed by the α-In2Se3 transistor array, where in-situ reward-based weight updates and eligibility trace decay are performed without any external memory or computing units. Our solution enables a fully functional, energy-efficient, and low-overhead spiking-based reinforcement learning architecture.