Multi-Agent Systems

Name: Multi-Agent Systems | 16th European Conference, EUMAS 2018, Bergen, Norway, December 6-7, 2018, Revised Selected Papers
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

16th European Conference, EUMAS 2018, Bergen, Norway, December 6-7, 2018, Revised Selected Papers

Marija Slavkovik(Herausgeber*in)

Springer (Verlag)

Erschienen am 14. Februar 2019

X, 267 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-030-14174-5 (ISBN)

53,49 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Preface
Organization
Contents
Temporal Epistemic Gossip Problems
1 Introduction
2 Definitions
3 Membership in NP
4 A Subproblem of the Temporal Gossip Problem in P
5 NP-completeness When Execution Time Is Bounded
6 NP-completeness of Gossiping with Negative Goals
7 Discussion and Conclusion
References
Partial and Full Goal Satisfaction in the MUSA Middleware
1 Introduction
2 Motivation
3 Full and Partial Goal Satisfaction
4 The Agent and Artifact Architecture
4.1 Implementing the Metric for Partial Satisfaction
5 Discussion
6 Conclusions
References
Generalising the Dining Philosophers Problem: Competitive Dynamic Resource Allocation in Multi-agent Systems
1 Introduction and Related Work
2 Generalisation of the Dining Philosophers Problem
3 Logic for Specification and Verification of GDP Games
4 Symbolic Representation of Configurations on GDP Games
5 Symbolic Verification of LGDP Formulae in GDP Games
6 Conclusions and Outlook to Future Work
A Appendix: Proof of Theorem1
References
Interpreting Information in Smart Environments with Social Patterns
1 Introduction
2 Background
3 The SCAA Framework
3.1 Social Information
3.2 Architecture
4 Case Study: Distributed Collaborative Care System
5 Related Work
6 Conclusions
References
Learning Hedonic Games via Probabilistic Topic Modeling
1 Introduction
2 Background and Related Work
2.1 Hedonic Games
2.2 Probabilistic Topic Modeling
2.3 Uncertainty
3 Game Interpretation as Documents
4 Experimental Evaluation
4.1 Dataset and Setting Escalation
4.2 Significant Agents and Valid Topics
4.3 Results
5 Conclusion and Future Work
A Appendix: Detailed Results
References
Learning Best Response Strategies for Agents in Ad Exchanges
1 Introduction
2 Related Work
3 Model for the Publisher in an Ad Exchange
3.1 HBA Types (Advertiser's Strategies)
3.2 HBA Beliefs and Best Responses
3.3 HBA Censored
3.4 KM Estimator for Stochastic Opponents
4 Experimental Results
4.1 Agents in the Type Space A
4.2 Neural Network Agent
5 Discussion and Conclusions
References
Towards Online Electric Vehicle Scheduling for Mobility-On-Demand Schemes
1 Introduction
2 Problem Formulation
3 Scheduling Algorithms
3.1 Short Mode Algorithm
3.2 Long Mode Algorithm
4 MOD Software Package
4.1 Web Platform
4.2 Mobile Application
5 Testing and Evaluation
6 Conclusions and Future Work
References
Two-Sided Markets: Mapping Social Welfare to Gain from Trade
1 Introduction
2 Preliminaries
3 Converting Social Welfare to Gain from Trade
4 Experimental Results
5 Conclusion and Discussion
References
Affective Decision-Making in Ultimatum Game: Responder Case
1 Introduction
2 Preliminaries
2.1 General Notation
2.2 Ultimatum Game Rules
2.3 Markov Decision Process
3 Ultimatum Game as Markov Decision Process: Responder's Strategy
3.1 Model of the Responder
3.2 Dynamic Programming in UG
4 Illustrative Experiments
4.1 Models of Proposer
4.2 Experiment Setup
4.3 Results
5 Conclusions
References
Implementing Argumentation-Enabled Empathic Agents
1 Introduction
2 Empathic Agent Concepts
3 Implementation of an Empathic Agent with Jason
4 Argumentation for Empathic Agents: Reaching Consensus in Case of Inconsistent Beliefs
5 Argumentation Semantics Analysis
6 Discussion
6.1 Argumentation and Jason
6.2 Alternative Negotiation Approaches
6.3 Limitations
6.4 Towards a Generic Empathic Agent
7 Conclusion
References
Towards Fully Probabilistic Cooperative Decision Making
1 Introduction
1.1 Paper Layout
1.2 Notions and Notation
2 Flat Multi-agents Systems
3 Single Agent Using FPD
3.1 Formulation and Solution of Fully Probabilistic Design
3.2 Certainty-Equivalent Receding-Horizon FPD
4 Multiple Agents Sharing Ideal Closed-Loop Models
4.1 Cooperation Circumstances
4.2 Question Related to Pooling for FPD
4.3 Algorithmic Summary
5 Experimental Part
5.1 Simulation Set Up
5.2 Commented Results
6 Concluding Remarks
References
Endorsement in Referral Networks
1 Introduction
2 Related Work
3 Background
3.1 Motivation
3.2 Referral Network Preliminaries
3.3 Proactive Skill Posting Preliminaries
4 Endorsement
5 Experimental Setup
6 Results
6.1 Robustness to Early Failures
6.2 Performance Gain
6.3 Tolerance to Noisy Self-skill Estimates
6.4 Incentive Compatibility
6.5 Generalizability of the Endorsement Framework
7 Conclusions and Future Work
References
Markov Chain Monte Carlo for Effective Personalized Recommendations
1 Introduction
2 Background and Related Work
2.1 Related Work
3 A Personalized Recommender System
3.1 Constraints
3.2 Beliefs Updating
3.3 Ranking the Items
3.4 Clustering
4 System Evaluation
4.1 Building the Synthetic Users
4.2 Experiments and Results
5 Conclusions and Future Work
References
Computing Consensus: A Logic for Reasoning About Deliberative Processes Based on Argumentation
1 Introduction
2 Background on Abstract Argumentation
3 Deliberative Dynamic Logic
4 Model Checking on Finitary Models
5 Conclusion and Future Work
References
Decentralized Multiagent Approach for Hedonic Games
1 Introduction
2 Preliminaries
3 Related Work
4 Methods
4.1 Decentralized Algorithm for Hedonic Games
4.2 Budding
4.3 Adapting the Decentralized Approach for Constrained Coalition Formation
5 Experiments
5.1 Unconstrained Coalition Hedonic Games
5.2 Constrained Coalition Hedonic Games
6 Results and Discussion
6.1 Results in Unconstrained Coalition Hedonic Games
6.2 Results in Constrained Coalition Hedonic Games
7 Conclusion
References
Deep Reinforcement Learning in Strategic Board Game Environments
1 Introduction
2 Background and Related Work
2.1 Deep Reinforcement Learning
2.2 Action-Dependent Features and Q-Decomposition
2.3 The Settlers of Catan (SoC) Domain
3 Our Approach
3.1 Local Q-Function Approximation
3.2 Deep Architecture
3.3 The DRRL Agent
4 Evaluation
4.1 Domain State Representation and Action Set
4.2 DRRL in the SoC Domain
4.3 Simulations and Results
5 Conclusions and Future Work
References
Counterfactually Fair Prediction Using Multiple Causal Models
1 Introduction
2 Background
2.1 Causality
2.2 Fairness
2.3 Opinion Pooling
3 Aggregation of Causal Models Under Fairness
3.1 Problem Formalization
3.2 Qualitative Aggregation over the Graph
3.3 .3em plus .1em minus .1emQuantitative Aggregation over the Distribution of the Predictor
3.4 Illustration
4 Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken