Q-Networks with Dynamically Loaded Biases for Personalization

机译：Q-Networks具有动态加载的偏差以进行个性化

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Personalization is ever more prevalent in digital systems in various application domains. Reinforcement learning is a method often applied to adjust a system's behavior to the user's preferences, but there are a number of hurdles when applying it in this context. We propose a novel neural network architecture for reinforcement learning agents specifically tailored to support personalization - Dynamically Loaded Biases Q-Network. We test our architecture on two environments simulating a personalization task and show that it can simultaneously learn a general behavior and adjust it to different environments.

机译：个性化在各种应用领域的数字系统中更普遍。强化学习是一种经常应用于将系统的行为调整到用户偏好的方法，但在此上下文中应用时存在许多障碍。我们提出了一种专门定制的强化学习代理的新型神经网络架构，以支持个性化 - 动态加载的偏置Q-network。我们在模拟个性化任务的两个环境中测试我们的体系结构，并显示它可以同时学习一般行为并将其调整到不同的环境。

著录项

来源
《IEEE World Symposium on Applied Machine Intelligence and Informatics》|2021年|000311-000316|共6页
会议地点
作者
Ján Magyar; Peter Sinčák;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Training; Digital systems; Neural networks; Reinforcement learning; Task analysis; Informatics; Machine intelligence;

机译：培训;数字系统;神经网络;加强学习;任务分析;信息学;机器智能;

相似文献

外文文献
中文文献
专利

1. Personalizing and externalizing biases in deluded and depressed patients: are attributional biases a stable and specific characteristic of delusions? [J] . Diez-Alegria C, Vazquez C, Nieto-Moreno M, The British journal of clinical psychology . 2006,第Pta4期

机译：个性化和外化偏头痛和抑郁症患者的偏见：归因偏见是否是妄想的稳定且特定的特征？
2. Dynamic fusion for ensemble of deep Q-network [J] . Chan Patrick P. K., Xiao Meng, Qin Xinran, International journal of machine learning and cybernetics . 2021,第4期

机译：深度Q网集合的动态融合
3. Deep Q-Network Based Dynamic Trajectory Design for UAV-Aided Emergency Communications [J] . Liang Wang, Kezhi Wang, Cunhua Pan, Journal of Communications and Information Networks . 2020,第4期

机译：基于深度Q网络的动态轨迹设计，用于无人机辅助紧急通信
4. Personalization of dynamically loaded service programs for a human-robot communication channel [C] . Kobayashi A., Kono Y., Ueno A., Robot and Human Interactive Communication, 2004. ROMAN 2004. 13th IEEE International Workshop on . 2004

机译：人机交互通道的动态加载服务程序的个性化
5. On the numerical solution of the dynamically loaded hydrodynamic lubrication of the point contact problem. [D] . Lim, Sang Gyu. 1990

机译：关于动载荷流体动力润滑点接触问题的数值解。
6. Learning the Dynamic Treatment Regimes from Medical Registry Data through Deep Q-network [O] . Ning Liu, Ying Liu, Brent Logan, -1

机译：通过深度Q网络从医疗注册数据中学习动态治疗方案
7. Deep Echo State Q-Network (DEQN) and Its Application in Dynamic Spectrum Sharing for 5G and Beyond [O] . Hao-Hsuan Chang, Lingjia Liu, Yang Yi 2020

机译：深度回声状态Q-network（DEQN）及其在5G及以后的动态频谱共享中的应用

Q-Networks with Dynamically Loaded Biases for Personalization

摘要

著录项

相似文献

相关主题

期刊订阅