Atjaunināt sīkdatņu piekrišanu

E-grāmata: Interactions In Multiagent Systems

(Chinese Univ Of Hong Kong, Hong Kong), (Tianjin Univ, China)
  • Formāts: 332 pages
  • Izdošanas datums: 31-Jul-2018
  • Izdevniecība: World Scientific Publishing Co Pte Ltd
  • Valoda: eng
  • ISBN-13: 9789813208759
Citas grāmatas par šo tēmu:
  • Formāts - PDF+DRM
  • Cena: 107,07 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Ielikt grozā
  • Pievienot vēlmju sarakstam
  • Šī e-grāmata paredzēta tikai personīgai lietošanai. E-grāmatas nav iespējams atgriezt un nauda par iegādātajām e-grāmatām netiek atmaksāta.
Interactions In Multiagent SystemsPalielināt
  • Formāts: 332 pages
  • Izdošanas datums: 31-Jul-2018
  • Izdevniecība: World Scientific Publishing Co Pte Ltd
  • Valoda: eng
  • ISBN-13: 9789813208759
Citas grāmatas par šo tēmu:

DRM restrictions

  • Kopēšana (kopēt/ievietot):

    nav atļauts

  • Drukāšana:

    nav atļauts

  • Lietošana:

    Digitālo tiesību pārvaldība (Digital Rights Management (DRM))
    Izdevējs ir piegādājis šo grāmatu šifrētā veidā, kas nozīmē, ka jums ir jāinstalē bezmaksas programmatūra, lai to atbloķētu un lasītu. Lai lasītu šo e-grāmatu, jums ir jāizveido Adobe ID. Vairāk informācijas šeit. E-grāmatu var lasīt un lejupielādēt līdz 6 ierīcēm (vienam lietotājam ar vienu un to pašu Adobe ID).

    Nepieciešamā programmatūra
    Lai lasītu šo e-grāmatu mobilajā ierīcē (tālrunī vai planšetdatorā), jums būs jāinstalē šī bezmaksas lietotne: PocketBook Reader (iOS / Android)

    Lai lejupielādētu un lasītu šo e-grāmatu datorā vai Mac datorā, jums ir nepieciešamid Adobe Digital Editions (šī ir bezmaksas lietotne, kas īpaši izstrādāta e-grāmatām. Tā nav tas pats, kas Adobe Reader, kas, iespējams, jau ir jūsu datorā.)

    Jūs nevarat lasīt šo e-grāmatu, izmantojot Amazon Kindle.

This compendium covers several important topics related to multiagent systems, from learning and game theoretic analysis, to automated negotiation and human-agent interaction. Each chapter is written by experienced researchers working on a specific topic in mutliagent system interactions, and covers the state-of-the-art research results related to that topic.The book will be a good reference material for researchers and graduate students working in the area of artificial intelligence/machine learning, and an inspirational read for those in social science, behavioural economics and psychology.
Foreword v
About the Editors vii
About the Contributors ix
1 Scalability of Multiagent Reinforcement Learning 1(18)
Yunkai Zhuang
Yujing Hu
Hao Wang
1.1 Introduction
1(2)
1.2 Coordinating Q-Learning
3(1)
1.3 Negotiation-based MARL
4(4)
1.4 Accelerating MARL by Equilibrium Transfer
8(4)
1.5 MARL Using Knowledge Transfer
12(8)
1.5.1 Value Function Transfer
12(1)
1.5.2 Selected Value Function Transfer
12(3)
1.5.2.1 Evaluation of local environmental dynamics
13(1)
1.5.2.2 The SVFT algorithm
14(1)
1.5.3 Model Transfer-based Game Abstraction
15(4)
2 Centralization or Decentralization? A Compromising Solution Toward Coordination in Multiagent Systems 19(24)
Chao Yu
Hongtao Lv
Hongwei Ge
Liang Sun
Jun Meng
Bingcai Chen
2.1 Introduction
20(2)
2.2 Social Norms and RL
22(1)
2.3 The Proposed Hierarchical Learning Framework
23(7)
2.3.1 The Principle of the Learning Framework
23(2)
2.3.2 Generation of Supervision Policies
25(2)
2.3.3 Adaption of Local Learning Behaviors
27(1)
2.3.4 Price of Anarchy and Monarchy
28(2)
2.4 Experiments and Results
30(9)
2.5 Related Work
39(2)
2.6 Conclusion
41(1)
Acknowledgments
42(1)
3 Making Efficient Reputation-Aware Decisions in Multiagent Systems 43(22)
Han Yu
Chunyan Miao
Bo An
Zhiqi Shen
Cyril Leung
3.1 Introduction
44(1)
3.2 Method
45(8)
3.2.1 Problem Formulation
45(4)
3.2.2 An Efficient Distributed Decision-Making Approach
49(4)
3.3 Results
53(10)
3.3.1 Theoretical Analysis
53(3)
3.3.2 Simulations
56(12)
3.3.2.1 Experiment settings
56(3)
3.3.2.2 Simulation results
59(4)
3.4 Discussions
63(1)
Acknowledgments
64(1)
4 Decision-Theoretic Planning in Partially Observable Environments 65(26)
Zongzhang Zhang
Mykel Kochenderfer
4.1 Introduction
66(2)
4.2 Partially Observable Markov Decision Processes
68(5)
4.2.1 MDPs
68(2)
4.2.2 POMDPs
70(3)
4.2.2.1 Belief updating
71(1)
4.2.2.2 Belief MDPs
71(1)
4.2.2.3 Policies and value functions
72(1)
4.3 Approaches to Offline Planning
73(10)
4.3.1 Exact Value Iteration
74(2)
4.3.2 Approximate Value Iteration
76(2)
4.3.2.1 Methods for initializing the value function
77(1)
4.3.3 Point-based Value Iteration Methods
78(5)
4.4 Approaches to Online Planning
83(4)
4.4.1 Branch and Bound
84(1)
4.4.2 Heuristic Search
84(1)
4.4.3 Monte Carlo Tree Search
85(2)
4.5 Covering-Number-based Planning Theories
87(2)
4.5.1 Covering Number
87(1)
4.5.2 Complexity of Approximate Planning
88(1)
4.6 Summary
89(2)
5 Multiagent Reinforcement Learning Algorithms Based on Gradient Ascent Policy 91(16)
Chengwei Zhang
Xiaohong Li
Zhiyong Feng
Wanli Xue
5.1 Introduction
92(1)
5.2 Gradient Ascent Algorithms
93(11)
5.2.1 The Original Gradient Ascent Algorithm: Infinitesimal Gradient Ascent (IGA)
94(2)
5.2.2 Algorithms Improving the Convergence Properties of IGA
96(4)
5.2.3 Algorithms Improving Social Welfare of IGA
100(4)
5.3 Dynamics of GA-MARL Algorithms
104(2)
5.4 Conclusions
106(1)
6 Task Allocation in Multiagent Systems: A Survey of Some Interesting Aspects 107(42)
Jun Wu
Lei Zhang
Yu Qiao
Chongjun Wang
6.1 Introduction
108(3)
6.2 Taxonomy Study on Task Allocation
111(5)
6.2.1 Taxonomy Study for MultiRobot Task Allocation
112(4)
6.2.2 Taxonomy Study of Other Subfields
116(1)
6.3 Allocating Constrained or Complex Tasks
116(6)
6.3.1 Allocating Tasks with Constraints
117(2)
6.3.2 Allocating Complex Tasks
119(3)
6.4 Task Allocation for Rational Agents
122(7)
6.4.1 Task Allocation via VCG-based Mechanisms
124(2)
6.4.2 Task Allocation Based on Optimal Mechanisms
126(1)
6.4.3 Task Allocation Based on Online Mechanisms
127(2)
6.5 Task Allocation for Networked Systems
129(5)
6.5.1 Task Allocation in Social Networks
129(3)
6.5.2 Task Allocation in Wireless Sensor Networks
132(2)
6.5.3 Other Researches for Networked Task Allocation
134(1)
6.6 Distributed Task Allocation
134(8)
6.6.1 The Contract Net Protocol
135(2)
6.6.2 Market-based Distributed Task Allocation
137(2)
6.6.3 Distributed Task Allocation via Coalition Formation
139(2)
6.6.4 Centralized and Distributed Model: Trade-offs
141(1)
6.7 Dynamic Task Allocation
142(4)
6.7.1 Allocating Dynamic Tasks
142(3)
6.7.2 Task Allocation for Dynamic Agents
145(1)
6.8 Conclusions
146(3)
7 Automated Negotiation: An Efficient Approach to Interaction Among Agents 149(30)
Siqi Chen
Gerhard Weiss
7.1 Introduction
150(1)
7.2 Automated Negotiation
150(11)
7.2.1 Negotiation Forms
152(2)
7.2.1.1 Single-issue versus multiissue negotiations
152(1)
7.2.1.2 Bilateral versus multilateral negotiations
152(1)
7.2.1.3 Sequential versus concurrent negotiations
153(1)
7.2.1.4 Complete versus incomplete information
153(1)
7.2.2 Negotiation Protocol
154(1)
7.2.2.1 Simultaneous offers
154(1)
7.2.2.2 Alternating offers
155(1)
7.2.3 Negotiation Approaches
155(6)
7.2.3.1 Heuristic approaches
156(2)
7.2.3.2 Game theoretic approaches
158(2)
7.2.3.3 Argumentation
160(1)
7.3 Characters of Complex Practical Negotiation
161(3)
7.3.1 Zero Prior Opponent Knowledge
161(1)
7.3.2 Continuous-Time Constraints
161(1)
7.3.3 Discounting Effect and Reservation Value
162(2)
7.4 State-of-the-Art
164(12)
7.4.1 Agents Based on Regression Techniques
164(5)
7.4.2 Agents Based on Transfer Learning
169(7)
7.5 Conclusion
176(1)
Acknowledgments
177(2)
8 Norm Emergence in Multiagent Systems 179(28)
Tianpei Yang
Jianye Hao
Zhaopeng Meng
Zan Wang
8.1 Introduction
180(2)
8.2 Norm Emergence Approaches
182(16)
8.2.1 Top-Down Approaches
183(4)
8.2.2 Bottom-Up Approaches
187(5)
8.2.3 Hierarchical Approaches
192(6)
8.3 The Influence of Fixed-Strategy Agents on Norm Emergence
198(8)
8.3.1 Introduction of Fixed-Strategy Agents
199(2)
8.3.2 The Influence of Fixed-Strategy Agents on Norm Adoption
201(3)
8.3.3 The Influence of the Placement Heuristics of Fixed-Strategy Agents
204(1)
8.3.4 The Influence of Late Intervention of Fixed-Strategy Agents
205(1)
8.4 Conclusion
206(1)
9 Diffusion Convergence in the Collective Interactions of Large-scale Multiagent Systems 207(22)
Yichuan Jiang
Yifeng Zhou
Fuhan Yan
Yunpeng Li
9.1 Introduction
208(1)
9.2 Diffusion Convergence of Collective Behaviors in MAS
209(1)
9.2.1 Collective Behaviors in MAS
209(1)
9.2.2 Diffusion Convergence
209(1)
9.3 Structured Diffusion Convergence versus Non-structured Diffusion Convergence
210(7)
9.3.1 Structured Diffusion Convergence
211(3)
9.3.2 Non-structured Diffusion Convergence
214(3)
9.3.3 The Comparison and Analysis of the Two Diffusion Mechanisms
217(1)
9.4 Homogeneous Diffusion Convergence versus Heterogeneous Diffusion Convergence
217(5)
9.4.1 Homogeneous Diffusion Convergence
217(2)
9.4.2 Heterogeneous Diffusion Convergence
219(3)
9.4.2.1 Agent's heterogeneity
220(1)
9.4.2.2 Interaction's heterogeneity
221(1)
9.4.3 The Comparison and Analysis of the Two Diffusion Mechanisms
222(1)
9.5 Neighboring Diffusion Convergence versus Global Diffusion Convergence
222(5)
9.5.1 Neighboring Diffusion Convergence
222(2)
9.5.2 Global Diffusion Convergence
224(3)
9.5.3 The Comparison and Analysis of the Two Diffusion Mechanisms
227(1)
9.6 Conclusion
227(2)
10 Incorporating Inference into Online Planning in Multiagent Settings 229(35)
Yingke Chen
Prashant Doshi
Jing Tang
Yinghui Pan
10.1 Introduction
229(4)
10.2 Individual Decision Making Frameworks
233(13)
10.2.1 Interactive Dynamic Influence Diagrams
234(8)
10.2.2 Solutions
242(4)
10.3 Online Planning with Limited Model Space
246(6)
10.3.1 Algorithm Outline
246(3)
10.3.2 Most Probable Model Selection
249(3)
10.4 Savings and PAC Bound
252(3)
10.5 Experimental Results
255(6)
10.6 Related Work
261(2)
10.7 Concluding Remarks
263(1)
Acknowledgments 264(1)
Bibliography 265(30)
Index 295
Biežāk uzdotie jautājumi par e-grāmatām Biežāk uzdotie jautājumi par e-grāmatām
Permanent link: https://www.kriso.lv/db/97898132087592e.html
Keywords: