Scholarlink

<p>The intrinsic gradient in organisms governs long-term information processing and continual learning in dynamic environments. Reinforcement learning (RL) aims to emulate such temporal regulation to enhance learning efficiency and adaptability. However, the absence of intrinsic gradient construction in existing memristive devices leads to stochastic and abrupt state changes, disrupting the generation of temporally correlated internal states critical for continual RL. In this work, a second-order memristor incorporating a stable intrinsic oxygen gradient was designed via a molecular-coordinated layer, which enables a prolonged dynamic barrier evolution (&gt;10<sup>2 </sup>s). This slow dynamic response facilitates balanced oxygen ion migration and diffusion under unipolar spike stimulation, resulting in a significant conductance modulation (Δ<i>G</i> = –98.1%). These temporally adaptive conductance states were quantitatively mapped to learning rates in the RL algorithm, allowing the learning task timescale to co-evolve with device dynamics. Compared with conventional strategies, intrinsic-gradient-driven modulation reduced training iterations by 68.75% and 35.65% in static and dynamic environments, respectively. These findings underscore the potential of slow-dynamic second-order memristors as physically grounded time-adaptive units bridging device dynamics and algorithmic learning in neuromorphic systems.</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

Intrinsic gradient oxygen-driven second-order memristors for continual reinforcement learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月3日

查看全文
  • Jianyu Ming,
  • Ruiheng Wang,
  • Jingwei Fu,
  • Jing Liu,
  • Siqi Wu,
  • Shanshuo Liu,
  • He Shao,
  • Yanfei Li,
  • Jin Wang,
  • Yiru Wang,
  • Xumeng Zhang,
  • Linghai Xie,
  • Haifeng Ling,
  • Wei Huang

摘要

The intrinsic gradient in organisms governs long-term information processing and continual learning in dynamic environments. Reinforcement learning (RL) aims to emulate such temporal regulation to enhance learning efficiency and adaptability. However, the absence of intrinsic gradient construction in existing memristive devices leads to stochastic and abrupt state changes, disrupting the generation of temporally correlated internal states critical for continual RL. In this work, a second-order memristor incorporating a stable intrinsic oxygen gradient was designed via a molecular-coordinated layer, which enables a prolonged dynamic barrier evolution (>102 s). This slow dynamic response facilitates balanced oxygen ion migration and diffusion under unipolar spike stimulation, resulting in a significant conductance modulation (ΔG = –98.1%). These temporally adaptive conductance states were quantitatively mapped to learning rates in the RL algorithm, allowing the learning task timescale to co-evolve with device dynamics. Compared with conventional strategies, intrinsic-gradient-driven modulation reduced training iterations by 68.75% and 35.65% in static and dynamic environments, respectively. These findings underscore the potential of slow-dynamic second-order memristors as physically grounded time-adaptive units bridging device dynamics and algorithmic learning in neuromorphic systems.