A Dynamic Programming Algorithm for Decentralized Markov Decision Processes with a Broadcast Structure

被引：13

作者：

Wu, Jeff ^{[1
]}

Lall, Sanjay ^{[1
]}

机构：

[1] Stanford Univ, Dept Elect Engn, Stanford, CA 94305 USA

来源：

49TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC) | 2010年

关键词：

COMPLEXITY;

D O I：

10.1109/CDC.2010.5718187

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We give an optimal dynamic programming algorithm to solve a class of finite-horizon decentralized Markov decision processes (MDPs). We consider problems with a broadcast information structure that consists of a central node that only has access to its own state but can affect several outer nodes, while each outer node has access to both its own state and the central node's state, but cannot affect the other nodes. The solution to this problem involves a dynamic program similar to that of a centralized partially-observed Markov decision process.

引用

页码：6143 / 6148

页数：6

共 50 条

[21] Towards Dynamic Pricing for Shared Mobility on Demand using Markov Decision Processes and Dynamic Programming
Guan, Yue
Annaswamy, Anuradha M.
Tseng, H. Eric
2020 IEEE 23RD INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), 2020,
[22] Linear programming solvers for Markov Decision Processes
Bello, Diego
Riano, German
2006 IEEE SYSTEMS AND INFORMATION ENGINEERING DESIGN SYMPOSIUM, 2006, : 90 - +
[23] Approximate linear programming for decentralized policy iteration in cooperative multi-agent Markov decision processes
Mandal, Lakshmi
Lakshminarayanan, Chandrashekar
Bhatnagar, Shalabh
SYSTEMS & CONTROL LETTERS, 2025, 196
[24] A Structure-aware Online Learning Algorithm for Markov Decision Processes
Roy, Arghyadip
Borkar, Vivek
Karandikar, Abhay
Chaporkar, Prasanna
PROCEEDINGS OF THE 12TH EAI INTERNATIONAL CONFERENCE ON PERFORMANCE EVALUATION METHODOLOGIES AND TOOLS (VALUETOOLS 2019), 2019, : 71 - 78
[25] ON STOCHASTIC DYNAMIC-PROGRAMMING - A BRIDGE BETWEEN MARKOV DECISION-PROCESSES AND GAMBLING
SCHAL, M
MARKOV PROCESS AND CONTROL THEORY, 1989, 54 : 178 - 216
[26] Variance-penalized Markov decision processes: dynamic programming and reinforcement learning techniques
Gosavi, Abhijit
INTERNATIONAL JOURNAL OF GENERAL SYSTEMS, 2014, 43 (06) : 649 - 669
[27] MARKOV DECISION-PROCESSES - DISCRETE STOCHASTIC DYNAMIC-PROGRAMMING - PUTERMAN,ML
THOMAS, LC
JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY, 1995, 46 (06) : 792 - 793
[28] Approximate dynamic programming with (min, plus ) linear function approximation for Markov decision processes
Chandrashekar, L.
Bhatnagar, Shalabh
2014 IEEE 53RD ANNUAL CONFERENCE ON DECISION AND CONTROL (CDC), 2014, : 1588 - 1593
[29] A COMPROMISE PROGRAMMING APPROACH TO MULTIOBJECTIVE MARKOV DECISION PROCESSES
Ogryczak, Wlodzimierz
Perny, Patrice
Weng, Paul
INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING, 2013, 12 (05) : 1021 - 1053
[30] A Dynamic Programming Approach for Ambient Intelligence Platforms in Running Sports Based on Markov Decision Processes
Vales-Alonso, J.
Lopez-Matencio, P.
Alcaraz, J. J.
Sieiro-Lomba, J. L.
Costa-Montenegro, E.
Gonzalez-Castano, F. J.
HUMAN-COMPUTER SYSTEMS INTERACTION: BACKGROUNDS AND APPLICATIONS 2, PT 1, 2012, 98 : 165 - +

← 1 2 3 4 5 →