188宝金博页面版

  • 图案背景
  • 纯色背景
视图
标记
批注
批注本地保存成功，开通会员云端永久保存 去开通
eqnyt1683

上传于：2015-12-31

粉丝量：1

该文档贡献者很忙，什么也没留下。


  • 相关
  • 目录
  • 笔记
  • 书签

188宝金博页面版:更多相关文档

  • Towards motivation-based decisions for worth goals

    星级： 10 页

  • towards motivation-based decisions for worth goals

    星级： 10 页

  • 【精品】Towards motivation-based decisions for worth goals

    星级： 10 页

  • [精品]GOALS

    星级： 2 页

  • 【精品】Goals

    星级： 65 页

  • 【精品】Goals

    星级： 18 页

  • 【精品】Goals

    星级： 8 页

  • towards a motivation-based approach for evaluating goals

    星级： 4 页

  • Towards a motivation-based approach for evaluating goals

    星级： 2 页

  • ［推荐精品］I have goals for my life

    星级： 5 页

  • 【精品】worth

    星级： 8 页

  • 【精品】14.1 Goals

    星级： 8 页

  • [精品]worth&worthy用法辨析

    星级： 2 页

  • 【精品】Haworth

    星级： 8 页

  • nulls_for_goals

    星级： 5 页

暂无目录

点击鼠标右键菜单,创建目录

    暂无笔记

    选择文本，点击鼠标右键菜单，添加笔记

    暂无书签

    在左侧文档中，点击鼠标右键，添加书签

    188宝金博页面版: 【精品】Towards motivation-based decisions for worth goals

    下载积分： 700

    内容提示： Towards Motivation-Based Decisions for Worth GoalsSteve J Munroe1, Michael Luck1, Mark d’Inverno21Electronics and Computer Science University of Southampton, Southampton, UK{sjm01r, mml}@ecs. soton. ac. uk2Computer Science, University ofWestminster, London, UKdinverm@wmin. ac. ukAbstract. In this paper we present a motivational mechanism to generate anddetermine the worth ofgoals and to represent various constraints involved in sat-isfying a goal. The work builds on the SMART agent framework and adds to t...

    文档格式：PDF | 页数：10 | 浏览次数：10 | 上传日期：2015-12-31 23:48:49 | 文档星级：
    Towards Motivation-Based Decisions for Worth GoalsSteve J Munroe1, Michael Luck1, Mark d’Inverno21Electronics and Computer Science University of Southampton, Southampton, UK{sjm01r, mml}@ecs. soton. ac. uk2Computer Science, University ofWestminster, London, UKdinverm@wmin. ac. ukAbstract. In this paper we present a motivational mechanism to generate anddetermine the worth ofgoals and to represent various constraints involved in sat-isfying a goal. The work builds on the SMART agent framework and adds to thegrowing body of work that is attempting to extend the abilities of autonomousagents past the constraints of the traditional symbolic approaches to AI. The pa-per represents a first step in increasing an agent’s autonomy in the domain of e-commerce, specifically enabling the agent to dynamically set issue parameters inrelation to the importance ofthe issue and the effects ofany existing constraints.1Overcoming the limitations of symbolically based representations as used in intelli-gent agents, to cope with more realistic domains, is an area growing in size. Workfrom robotic control [14], design to criteria scheduling [19] and cognitive appraisal the-ory [16] all pertain to extending the abilities of computational agents into continuous,worth-oriented domains. Trading-off the satisfaction of multiple issues or goals in thecontext of conflicting constraints however, has had little attention as yet in the field ofautonomous deliberative agents (cf. [17]), though workrelevant to this exists in auctionsin the case of multiple-issues (eg. [2]) and robotic control in the case of synthesisingbehaviour in the face of multiple constraints (eg. [14]). Traditional deliberative agentarchitectures (eg. [11]) tend to employ a static representation of preferences that anagent must try to satisfy with little or no room for adjusting them in the light of newinformation. Often it is not possible however, to fully satisfy existing goals in a par-ticular environment and, lacking any way to relax goals, they are therefore likely to bedropped, and the associated utility gain lost.Within the field ofelectronic commerce, recent advances in agents are allowing au-tomation of many activities usually performed by humans. Agents are now able to usesimple negotiation strategies in order to purchase a good or a service under conditionsthat best satisfy a user’s preferences (eg. [8]). The dominant approach to the worth-oriented nature of such a domain is to use utility-based, selfish maximising agents (eg,[5]). However, take up of these new systems is generally limited to simple purchasesover one issue such as price, in which user preferences are rigidly encoded, offering lit-tle opportunity for flexible yet robust adaptation to prevailing circumstances. It wouldbe desirable to be able to combine both approaches to see how to increase an agent’sautonomy with respect to making purchasing decisions in the face ofdynamic environ-ments and changing contexts.Introduction

    阅读了该文档的用户还阅读了这些文档

    188宝金博页面版:关于我们

    188宝金博页面版:帮助中心

    188宝金博页面版:关注我们

    • 新浪微博

    关注188宝金博页面版公众号

    188宝金博页面版
    阅读
    APP
    阅读
    返回
    顶部
    188宝金博页面版官网登录在线平台入口（2026已更新）—江苏协昌电子科技股份有限公司