ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Stimulus sampling as an exploration mechanism for fast reinforcement learning

Vladimirskiy, Boris B.*; Vasilaki, Eleni; Urbanczik, Robert; Senn, Walter
Biological Cybernetics2009-4DOI: 10.1007/s00422-009-0305-x
2被引3阅读
引用收藏
分享

摘要

Reinforcement learning in neural networks requires a mechanism for exploring new network states in response to a single, nonspecific reward signal. Existing models have introduced synaptic or neuronal noise to drive this exploration. However, those types of noise tend to almost average out-precluding or significantly hindering learning -when coding in neuronal populations or by mean firing rates is considered. Furthermore, careful tuning is required to find the elusive balance between the often conflicting demands of speed and reliability of learning. Here we show that there is in fact no need to rely on intrinsic noise. Instead, ongoing synaptic plasticity triggered by the naturally occurring online sampling of a stimulus out of an entire stimulus set produces enough fluctuations in the synaptic efficacies for successful learning. By combining stimulus sampling with reward attenuation, we demonstrate that a simple Hebbian-like learning rule yields the performance that is very close to that of primates on visuomotor association tasks. In contrast, learning rules based on intrinsic noise (node and weight perturbation) are markedly slower. Furthermore, the performance advantage of our approach persists for more complex tasks and network architectures. We suggest that stimulus sampling and reward attenuation are two key components of a framework by which any single-cell supervised learning rule can be converted into a reinforcement learning rule for networks without requiring any intrinsic noise source.

学科与关键词

关键词
Online learningHebbian learningAssociation task-NoiseRewardPunishmentReward attenuationHippocampusMedial temporal lobeStriatum
相关
加载中…
  • Functional Requirements for Reward-Modulated Spike-Timing-Dependent Plasticity
    Fremaux, Nicolas; Sprekeler, Henning; Gerstner, WulframJournal of Neuroscience, 2010, 30(40): 13326-13337.被引 88
  • Learning predictive cognitive maps with spiking neurons during behavior and replays
    Bono, Jacopo; Zannone, Sara; Pedrosa, Victor; Clopath, Claudia*eLife, 2023, 12: e80671.被引 11
  • From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation
    Soltoggio, Andrea*; Stanley, Kenneth O.Neural Networks, 2012, 34: 28-41.被引 22
查看全部 →

发表信息

论文状态
公开发表
期刊
Biological Cybernetics
发表日期
2009-04
卷期
第 100 卷, 第 4 期
页码
319-330
DOI
10.1007/s00422-009-0305-x
语言
ENGLISH
成果收录
SCIE

作者

  • V

    Vladimirskiy, Boris B. (通讯) (第一作者)

  • V

    Vasilaki, Eleni

查看全部 4 位作者收起作者
  • U

    Urbanczik, Robert

  • S

    Senn, Walter

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417