国产bbaaaaa片,成年美女黄网站色视频免费,成年黄大片,а天堂中文最新一区二区三区,成人精品视频一区二区三区尤物

首頁(yè)> 外文學(xué)位 >A planner-independent approach to human-interactive planning.
【24h】

A planner-independent approach to human-interactive planning.

機(jī)譯：與計(jì)劃者無(wú)關(guān)的人機(jī)交互計(jì)劃方法。

獲取原文
獲取原文并翻譯 | 示例
  • 摘要
  • 著錄項(xiàng)
  • 相似文獻(xiàn)
  • 相關(guān)主題

摘要

This dissertation introduces a novel approach to the problem of human-interactive planning (HIP), in which a human user and an intelligent planning agent collaboratively develop plans. Many AI researchers have realized the potential of "human-in-the-loop" in plan development. Not only does joint plan development between human users and planning systems overcome some limitations of fully automated AI planning systems, but it also increases user's trust in the end product as well as complements the intuitive planning skills of human experts with the superior bookkeeping capabilities of automated planning systems.;Putting human users in the loop of plan development, however, creates many additional requirements that differ from what classical AI planning systems require in general, including a communication protocol in which the system and a human user can communicate each other, and additional components (e.g., natural language processing (NLP)) to support these communications. Integrating these different components is also another big issue in developing HIP systems. Due to the fact that they are traditionally studied in isolation, the integration is hard, but the individual update and modification is much harder than that. It causes isolation and disconnection of HIP research from mainstream planning research and contributes to the obsolescence of the planning technologies underlying HIP systems.;This work shows a way to effectively exploit classical AI planning techniques within the context of human-interactive planning. It can be achieved by changing the target of communication. In our approach, the communication of the underlying planning system with other modules, including human users, happens in the surface level, i.e., it's about the inputs to the planning system, not about the detail of inside the planning process. This effort makes it possible to directly utilize classical one-shot planning techniques---that take a fixed set of goals, initial state, and a domain theory---to support the hierarchical, gradual, and exploratory nature of human-interactive planning. Because this approach doesn't require to control inside the planning system, it is planner-independent---in that it could incorporate any classical planning technique. It recasts the problem of human-interactive planning as a search through a space of possible inputs to a classical planning system. This work can bridge HIP and classical AI planning communities that have traditionally evolved in parallel so that they can leverage each other's development and improvement. Although ideally suitable for intelligent agents that must plan interactively and collaboratively with humans, the technique suggests ways to enhance multi-agent planning in general.
機(jī)譯：本文介紹了一種新的方法來(lái)解決人機(jī)交互計(jì)劃（HIP），其中人類用戶和智能計(jì)劃代理共同開(kāi)發(fā)計(jì)劃。許多AI研究人員已經(jīng)意識(shí)到計(jì)劃開(kāi)發(fā)中“人在循環(huán)中”的潛力。人類用戶和計(jì)劃系統(tǒng)之間的聯(lián)合計(jì)劃開(kāi)發(fā)不僅克服了全自動(dòng)AI計(jì)劃系統(tǒng)的某些局限性，而且還提高了用戶對(duì)最終產(chǎn)品的信任，并通過(guò)自動(dòng)化的卓越簿記功能補(bǔ)充了人類專家的直觀計(jì)劃技能但是，將人類用戶置于計(jì)劃開(kāi)發(fā)的循環(huán)中會(huì)產(chǎn)生許多其他要求，這些要求通常不同于傳統(tǒng)的AI計(jì)劃系統(tǒng)，包括系統(tǒng)和人類用戶可以相互通信的通信協(xié)議，以及支持這些通信的其他組件（例如自然語(yǔ)言處理（NLP））。集成這些不同的組件也是開(kāi)發(fā)HIP系統(tǒng)的另一個(gè)大問(wèn)題。由于傳統(tǒng)上是對(duì)它們進(jìn)行單獨(dú)研究的事實(shí)，因此很難進(jìn)行集成，但是單獨(dú)的更新和修改要困難得多。它導(dǎo)致HIP研究與主流計(jì)劃研究之間的隔離和脫節(jié)，并導(dǎo)致HIP系統(tǒng)底層的計(jì)劃技術(shù)過(guò)時(shí)。;這項(xiàng)工作顯示了一種在人機(jī)交互計(jì)劃的背景下有效利用經(jīng)典AI計(jì)劃技術(shù)的方法。可以通過(guò)更改通信目標(biāo)來(lái)實(shí)現(xiàn)。在我們的方法中，底層計(jì)劃系統(tǒng)與其他模塊（包括人類用戶）的通信發(fā)生在表面上，即與計(jì)劃系統(tǒng)的輸入有關(guān)，而與計(jì)劃過(guò)程內(nèi)部的細(xì)節(jié)無(wú)關(guān)。這項(xiàng)工作可以直接利用經(jīng)典的一次性計(jì)劃技術(shù)-采取一組固定的目標(biāo)，初始狀態(tài)和領(lǐng)域理論-來(lái)支持人機(jī)交互計(jì)劃的層次，漸進(jìn)和探索性。因?yàn)榇朔椒ú恍枰谟?jì)劃系統(tǒng)內(nèi)部進(jìn)行控制，所以它與計(jì)劃者無(wú)關(guān)，因?yàn)樗梢院喜⑷魏谓?jīng)典的計(jì)劃技術(shù)。它通過(guò)在經(jīng)典計(jì)劃系統(tǒng)的可能輸入空間中進(jìn)行搜索來(lái)重現(xiàn)人機(jī)交互計(jì)劃的問(wèn)題。這項(xiàng)工作可以將傳統(tǒng)上并行發(fā)展的HIP和傳統(tǒng)AI規(guī)劃社區(qū)架起橋梁，以便他們可以相互利用和發(fā)展。盡管非常適合必須與人類進(jìn)行交互和協(xié)作計(jì)劃的智能代理，但該技術(shù)還是建議了總體上增強(qiáng)多代理計(jì)劃的方法。

著錄項(xiàng)

相似文獻(xiàn)

  • 外文文獻(xiàn)
  • 中文文獻(xiàn)
  • 專利
獲取原文

客服郵箱：kefu@zhangqiaokeyan.com

京公網(wǎng)安備：11010802029741號(hào) ICP備案號(hào)：京ICP備15016152號(hào)-6 六維聯(lián)合信息科技 (北京) 有限公司?版權(quán)所有

  • 客服微信

  • 服務(wù)號(hào)