Multi-Agent-Based Simulation XXI: 21st International Workshop, MABS 2020, Auckland, New Zealand, May 10, 2020, Revised Selected Papers (Lecture Notes in Computer Science)

Preface
Organization
Contents
Adaptivity in Distributed Agent-Based Simulation: A Generic Load-Balancing Approach
	1 Introduction
	2 Adaptivity in Agent-Based Simulation
	3 Distributed Simulation Architecture: Acsim
	4 MAPE-K as a Generic Framework for Adaptivity
	5 Motivating Examples
		5.1 Adaptive Local Optimization of Compute Cost - A Micro-traffic Example
		5.2 Adaptive Local Optimization of Communication Cost - A Cellular Automata Example
	6 Conclusion
	References
Trajectory Modelling in Shared Spaces: Expert-Based vs. Deep Learning Approach?
	1 Introduction
	2 Methodology
		2.1 Problem Formulation
		2.2 Game-Theoretic Social Force Model
		2.3 LSTM with DBSCAN
	3 Data Sets and Evaluation Metrics
		3.1 Data Sets
		3.2 Evaluation Metrics
	4 Experimental Results
		4.1 Quantitative Results for Individual Models
		4.2 Qualitative Results for Individual Models
		4.3 Pros and Cons of GSFM and LSTM-DBSCAN
	5 Conclusion and Future Work
	References
Towards Agent-Based Traffic Simulation Using Live Data from Sensors for Smart Cities
	1 Introduction
	2 Collecting Traffic Counts
	3 The Liverpool Smart Pedestrians Project
	4 An Edge Computing Device for Traffic Monitoring
	5 Using Live Data in Traffic Simulation
	6 Preliminary Results
	7 Conclusion and Future Work
	References
Design and Evaluations of Multi-agent Simulation Model for Electric Power Sharing Among Households
	1 Introduction
	2 Related Works
	3 Assumption of Electric Power Sharing
		3.1 Outline of Electric Power Sharing Service
		3.2 Assumptions
	4 Design of MAS Model
		4.1 Household Agent
		4.2 Electricity Retailer Agent
	5 Basic Evaluation of Electric Power Sharing MAS Model
		5.1 Evaluation Policy
		5.2 Evaluation Indicator
		5.3 Input Data
		5.4 Conditions for Basic Evaluation
		5.5 Evaluation Results
		5.6 Analysis
	6 Conclusion
	References
Active Screening on Recurrent Diseases Contact Networks with Uncertainty: A Reinforcement Learning Approach
	1 Introduction
	2 Problem Statement
	3 Challenges
	4 Partially Observable States
	5 Combinatorial Maximization Problem
		5.1 Incremental Selection
		5.2 One-Shot Selection
	6 High-Dimensional State-Action Space
		6.1 One-Hot Encoding
		6.2 Nodewise Encoding
		6.3 Graph Convolutional Neural Networks
	7 Experiments
		7.1 Experiment Setup
		7.2 Experiment Result
	8 Conclusion
	9 Appendix
		9.1 Belief Update
	References
Impact of Meta-roles on the Evolution of Organisational Institutions
	1 Introduction
	2 An Overview of the Extended BDI Architecture
	3 Meta-roles and Role Dynamics
	4 Simulation, Algorithms, and Parameters
		4.1 Assumptions
		4.2 Societies
		4.3 Algorithms
		4.4 Parameters
	5 Results
		5.1 Permissions for Private Trade
		5.2 Fired Violators (Monitoring Strength)
	6 Discussion and Concluding Remarks
	References
Optimization of Large-Scale Agent-Based Simulations Through Automated Abstraction and Simplification
	1 Motivation
	2 Related Work
	3 Simplification Types
		3.1 Subsampling
		3.2 Simplifying Agents\' Decision Process
		3.3 Selectively Replacing Groups of Agents with One Agent
		3.4 Simplifying Communication Between Agents
	4 Experiments
		4.1 Simplifications Support in FARM
		4.2 GitHub and Twitter Simulations
		4.3 Experiment Setup
	5 Results
	6 Semi-automated Search for Effective Simplifications
	7 Conclusions and Future Work
	References
Improved Travel Demand Modeling with Synthetic Populations
	1 Introduction
	2 State of the Art in Mobility Modeling
	3 The Synthetic Population Approach
	4 Comparison of Results
		4.1 Trip Counts Comparison
		4.2 Departure Time Comparison
		4.3 Spatial Distribution Comparison
	5 Conclusion
	References
Author Index