云南高校图书馆联盟文献共享服务平台- N-POLICY

N-POLICY: 作品数：12被引量：17H指数：2; 导出分析报告; 相关领域：自动化与计算机技术更多>>; 相关机构：电子科技大学哈尔滨工业大学沈阳工业大学更多>>; 相关期刊：《IEEE/CAA Journal of Automatica Sinica》《Journal of Systems Science and Systems Engineering》《Journal of the Operations Research Society of China》《Social Sciences in China》更多>>; 相关基金：国家自然科学基金国家教育部博士点基金河北省自然科学基金更多>>

On-Policy and Off-Policy Value Iteration Algorithms for Stochastic Zero-Sum Dynamic Games: 《Journal of Systems Science & Complexity》2025年第1期421-435,共15页GUO Liangyuan WANG Bing-Chang ZHANG Ji-Feng; supported by the National Natural Science Foundation of China under Grant Nos.62122043,62192753,62433020,T2293770;Natural Science Foundation of Shandong Province for Distinguished Young Scholars under Grant No.ZR2022JQ31.; This paper considers the value iteration algorithms of stochastic zero-sum linear quadratic games with unkown dynamics.On-policy and off-policy learning algorithms are developed to solve the stochastic zero-sum games,...; 关键词：Approximate dynamic programming on-policy off-policy stochastic zero-sum games valueiteration

Robust Offline Actor-Critic With On-policy Regularized Policy Evaluation: 《IEEE/CAA Journal of Automatica Sinica》2024年第12期2497-2511,共15页Shuo Cao Xuesong Wang Yuhu Cheng; supported in part by the National Natural Science Foundation of China(62176259,62373364);the Key Research and Development Program of Jiangsu Province(BE2022095)。; To alleviate the extrapolation error and instability inherent in Q-function directly learned by off-policy Q-learning(QL-style)on static datasets,this article utilizes the on-policy state-action-reward-state-action(SA...; 关键词：Offline reinforcement learning off-policy QL-style on-policy SARSA-style policy evaluation(PE) Q-value estimation

Erratum to:Equilibrium Joining Strategies in the M/M/1 Queues with Setup Times under N-Policy: 《Journal of Systems Science and Systems Engineering》2022年第4期512-512,共1页Yaqian Hao Jinting Wang Zhongbin Wang Mingyu Yang; The article“Equilibrium Joining Strategies in the M/M/1 Queues with Setup Times under N-Policy”unfortunately contained a mistake about the first author’s affiliation.In the original publication of the paper,this af...; 关键词：M/M/1 TIMES SETUP

Equilibrium Joining Strategies in the M/M/1 Queues with Setup Times under N-Policy被引量：4: 《Journal of Systems Science and Systems Engineering》2019年第2期141-153,共13页Yaqian Hao Jinting Wang Zhongbin Wang Mingyu Yang; the National Natural Science Foundation of China under Grant Nos.71871008 and 71571014.; This paper carries out a game-theoretic analysis of a single-server queueing system with setup times under N-policy by considering both the partially observable and the partially unobservable information scenarios. Th...; 关键词：M/M/1 QUEUE SETUP time N-POLICY EQUILIBRIUM information

The Determinants of the Italian Support to International Criminal Courts: 《International Relations and Diplomacy》2016年第12期737-745,共9页Claudia Pividori; Since the beginning of the 1990s, Italian foreign policy actors have showed a steady and bipartisan commitment to international criminal justice institutions, the International Criminal Tribunal for the former Yugosla...; 关键词：ITALY International Criminal Tribunals foreign-policy role theory

N-policy for M^(x)/G/1 Unreliable Retrial G-Queue with Preemptive Resume and Multi-services被引量：1: 《Journal of the Operations Research Society of China》2016年第4期437-459,共23页Amita Bhagat Madhu Jain; Bulk arrival retrial G-queue with impatient customers and multi-servicessubject to server breakdowns has been analyzed. The system allows the arrival oftwo types of customers: positive customers and negative customers...; 关键词：Retrial queue N-policy vacation Negative customers RENEGING Bulk arrival Breakdowns Preemptive resume Multi-services

M/G/1 Vacation Queueing Systems with Server Timeout被引量：2: 《American Journal of Operations Research》2015年第2期77-88,共12页Oliver C. Ibe; We consider a single-server vacation queueing system that operates in the following manner. When the server returns from a vacation, it observes the following rule. If there is at least one customer in the system, the...; 关键词：VACATION QUEUEING Systems TIMEOUT POLICIES Performance Analysis N-POLICY with TIMEOUT

Delay optimization for planar wireless sensor network with N-policy被引量：1: 《Journal of Central South University》2014年第12期4537-4543,共7页陈志刚张德宇陈龙; Projects(61379110,61379057,61073186)supported by the National Natural Science Foundation of China;Project(2013zzts043)supported by the Fundamental Research Funds for the Central Universities,China; In N-policy, the nodes attempt to seize the channel when the number of packets in the buffer approaches N. The performance of N-policy on the energy efficiency is widely studied in the past years. And it is presented ...; 关键词：wireless sensor network N-policy delay energy-efficiency M/M/1

Stochastic Design of Enhanced Network Management Architecture and Algorithmic Implementations被引量：1: 《American Journal of Operations Research》2013年第1期87-93,共7页Song-Kyoo Kim; The paper is focused on available server management in Internet connected network environments. The local backup servers are hooked up by LAN and replace broken main server immediately and several different types of b...; 关键词：STOCHASTIC Network Management N-POLICY CLOSED QUEUE Algorithmic Implementation STOCHASTIC Optimization

THE RECURSIVE SOLUTION OF QUEUE LENGTH FOR Geo/G/1 QUEUE WITH N-POLICY被引量：8: 《Journal of Systems Science & Complexity》2012年第2期293-302,共10页Chuanyi LUO Yinghui TANG Wei LI Kaili XIANG; supported by the National Natural Science Foundation of China under Grant No.70871084;The Specialized Research Fund for the Doctoral Program of Higher Education of China under Grant No. 200806360001;a grant from the "project 211(PhaseⅢ)" of the Southwestern University of Finance and Economics, Scientific Research Fund of Southwestern University of Finance and Economics; This paper considers a discrete-time queue with N-policy and LAS-DA(late arrival system with delayed access) discipline.By using renewal process theory and probability decomposition techniques,the authors derive the r...; 关键词：Discrete-time queue N-POLICY recursive expression stochastic decomposition.

N-POLICY