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 >Agent interactions in decentralized environments.
【24h】

Agent interactions in decentralized environments.

機(jī)譯：分散環(huán)境中的代理交互。

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

The decentralized Markov decision process (Dec-POMDP) is a powerful formal model for studying multiagent problems where cooperative, coordinated action is optimal, but each agent acts based on local data alone. Unfortunately, it is known that Dec-POMDPs are fundamentally intractable: they are NEXP-complete in the worst case, and have been empirically observed to be beyond feasible optimal solution.;To get around these obstacles, researchers have focused on special classes of the general Dec-POMDP problem, restricting the degree to which agent actions can interact with one another. In some cases, it has been proven that these sorts of structured forms of interaction can in fact reduce worst-case complexity. Where formal proofs have been lacking, empirical observations suggest that this may also be true for other cases, although less is known precisely.;This thesis unifies a range of this existing work, extending analysis to establish novel complexity results for some popular restricted-interaction models. We also establish some new results concerning cases for which reduced complexity has been proven, showing correspondences between basic structural features and the potential for dimensionality reduction when employing mathematical programming techniques.;As our new complexity results establish that worst-case intractability is more widespread than previously known, we look to new ways of analyzing the potential average-case difficulty of Dec-POMDP instances. As this would be extremely difficult using the tools of traditional complexity theory, we take a more empirical approach. In so doing, we identify new analytical measures that apply to all Dec-POMDPs, whatever their structure. These measures allow us to identify problems that are potentially easier to solve on average, and validate this claim empirically. As we show, the performance of well-known optimal dynamic programming methods correlates with our new measure of difficulty. Finally, we explore the approximate case, showing that our measure works well as a predictor of difficulty there, too, and provides a means of setting algorithm parameters to achieve far more efficient performance.
機(jī)譯：分散的馬爾可夫決策過(guò)程（Dec-POMDP）是一個(gè)功能強(qiáng)大的正式模型，用于研究多主體問(wèn)題，其中合作，協(xié)調(diào)的行動(dòng)是最佳的，但每個(gè)主體僅基于本地?cái)?shù)據(jù)進(jìn)行行動(dòng)。不幸的是，眾所周知Dec-POMDP從根本上是難于解決的：在最壞的情況下它們是NEXP完全的，并且從經(jīng)驗(yàn)上已經(jīng)觀察到它們超出了可行的最佳解決方案。為了解決這些障礙，研究人員將注意力集中在特殊的Dec-POMDP的一般性問(wèn)題，它限制了代理程序行為可以相互交互的程度。在某些情況下，已經(jīng)證明，這種類型的結(jié)構(gòu)化交互形式實(shí)際上可以減少最壞情況下的復(fù)雜性。在缺乏正式證據(jù)的情況下，經(jīng)驗(yàn)觀察表明，盡管對(duì)其他情況的確切了解很少，但對(duì)其他情況也可能是正確的。本論文統(tǒng)一了一系列現(xiàn)有工作，擴(kuò)展了分析范圍，以建立一些流行的受限相互作用的新穎復(fù)雜性結(jié)果楷模。我們還建立了一些有關(guān)已證明降低了復(fù)雜性的案例的新結(jié)果，顯示了采用數(shù)學(xué)編程技術(shù)時(shí)基本結(jié)構(gòu)特征與降維潛力之間的對(duì)應(yīng)關(guān)系。由于我們的新復(fù)雜性結(jié)果表明，最壞情況下的可處理性比以前已知，我們尋求分析Dec-POMDP實(shí)例潛在平均案例難度的新方法。由于使用傳統(tǒng)復(fù)雜性理論的工具很難做到這一點(diǎn)，因此我們采用了更為經(jīng)驗(yàn)的方法。通過(guò)這樣做，我們確定了適用于所有Dec-POMDP的新分析方法，無(wú)論其結(jié)構(gòu)如何。這些措施使我們能夠確定平均而言可能更容易解決的問(wèn)題，并憑經(jīng)驗(yàn)驗(yàn)證這一說(shuō)法。正如我們所展示的那樣，眾所周知的最佳動(dòng)態(tài)規(guī)劃方法的性能與我們的新難度度量相關(guān)。最后，我們探索了近似情況，表明我們的度量也可以很好地預(yù)測(cè)困難，并提供了一種設(shè)置算法參數(shù)的方法，以實(shí)現(xiàn)更高效率的性能。

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)