Agent-Ba Base sed Sim imula lation ion Dagstuhl Seminar Modeling - PowerPoint PPT Presentation

Agent-Ba Base sed Sim imula lation ion Dagstuhl Seminar „Modeling and Analysis of Semiconductor Supply Chains“ February 10 th , 2016 Dr. Iris is Lorsc rsche heid id Hamburg burg University iversity of Techn hnology, ology, Germ rmany any www.tuhh. tuhh.de de/mac /maccs cs - Institute titute of Mana nage gemen ent t Accounting counting and Sim imula lation tion 1

A few words about myself… Current research – Using Structural al Equation on Models (SEM-PLS) LS) to emp mpirical ally y valida date e agent architec ectures res (see, e.g., Lorscheid et al. 2014) and to analyz yze simulated d data (see, e.g., Mertens et al. 2015). – Developing standards rds for the design n of simulation n experime riment nts and analys ysis s of (complex) simulation models (see, e.g., Lorscheid et al. 2012, Lorscheid and Meyer in press). – Learni ning g agents for human complex systems (see, e.g., Lorscheid 2014). Community – European Social Simulation Association (ESSA) http://www.essa.eu.org 2

Perspect ctive ives s on agent-base sed sim imula lation ion and it its contr tribu ibution tion Analyzing Emergence Incorporating human behavior Using artificial agents 3

About emergence… • https://www.youtube.com/watch?v=KGeg mMWsgu8 4

Fir irst step: Underst rstand anding ing in indiv ividu idual l behavio vior Decision rules: 1. Separation - avoid crowding neighbors (short range repulsion) 2. Alignment - steer towards average heading of neighbors 3. Cohesion - steer towards average position of neighbors (long range attraction) 5

Sim imula lation: ion: Flo lockin king behavior vior 6

Syste tem m Behavio avior r is is t the Result lt of Indiv ividu idual l Actio ion Macr cro level vel Interaction of individuals System success? Micr cro level vel Behavior rules Preferences Perceptions (Information) Communication Agent behavio avior Individual Strategies 7

„If you grow the phenomena you‘ll understand how it works.“ Joshua M. Epstein Through the bottom-up design, self lf-org organiza nization tion and emergent nt processes sses may evolve that are not explic licit itly ly modelled lled (or even understood by the modeler!) Macal and North 2010 8

Perspect ctive ives s on agent-base sed sim imula lation ion and it its contr tribu ibution tion  Analyzing Emergence Incor orpor orat ating ing huma man n be behavio vior Using artificial agents 9

Agent Agent attributes Representing the decision rules of the • agent explicitly adaptive social autonom. re-/proactive Representing the interdependencies • between the different human Agent activities Action Perception Modelling the individual heterogeneity • of agents Environment Decision rules, Preferences, Perceptions 10

What are the effect cts s of varying ying decis isio ion models? ls? • Approaching more complex („human“) behavior models… • Perfect / rational Agents Human decision makers • decision maker • (homo oeconomicus) • … to explore possible consequences Preferences, Information, Condition -> Action Rules etc. 11

How w do we in inform m the decis isio ion n makers s wit ith ABM? 1. ABM asks new questions, like: – What are the individual strategies? Empirical study – What is the „human factor“ in your processes? – What are the interactions? 2. Implementation of findings in an ABM to analyze the effect. Modeling & – How big is the difference that it makes? Simulation – How robust ist the system? study – What are better ways of designing your environment? ABM is about understa standing nding the effects of human behavior to change (vs. tool to support local decisions) 12

Under erst stand and huma man n behavior vior to design ign your ur envir iron onme ment! nt! 13

Under erst stand and huma man n behavior vior to design ign your ur envir iron onme ment! nt! „As well as you need to make sure that people escape safely, you need to give them tools to make sure that they not get stucked in planning .“ 1. Understand human (re-)actions. 2. Design your walls and columns! 14

How to unde derstand stand human behavior? 15

How w to understa stand nd human man behavior vior? • Surveys, interviews, lab experiments • Using theories, such as – Prospect theory (Kahnemann/Tversky 1979) – Learning algorithms – See: Bounded rationality / behavioral economics • New ways, e.g.: – Using structural equation models for agent modeling (Lorscheid et al. 2014: The PLS Agent - Agent Behavior Validation by Partial Least Squares. Social Simulation Conference ) 16

Examp mple le from m the Infin ineo eon n project: ct: Supply ly chain in pla lanner Personal Experience Work Shadowing Field Qualitative Research Research Interviews General IFX Information Flow (Blumberg and Atre (2003) estimate that around 85% of business information does not exist in a structured way) 17

The in influ luencing cing facts s of a d decis isio ion (Infine fineon on) IFX Planning What are central aspects of Processes planning, affected by human Work decisions? Planning Environ- Tools ment • Where are individual deviations? Decision • What are the difficult Product Planning Behavior Specifics Reports situations? (beyond of a SCP pressing the button) • How do newcomers learn to act? Business Rules/ Guidelines/ Environ- Targets ment Personal • (…) Experience 18

Dir irect in interactions tions of the pla lannin ing agent 19

Data collec llectio ion n research ch design ign Qualitative Research Information Content Infineon Conceptual Modelling & Processes Model Simulation Continuous development & improvement of Scientific the current IFX processes Literature Level of Detail Königer 2016 20

How to mode del human behavior? 21

Sim imple le agent archit itectur cture Agent x S f(x) = a Rules Environment a A 22

Knowle owledgebase ase 23

Learning ing as addit itio ional l featur ure e to in increase se autonomy onomy x state of the environment y new enviornmental state z hidden factors influencing the outcome of the agents’ decision r reward a agents ‘ action 24

Category egory Divisi sion Manager er Learn arning model el requireme ements (A) K Knowledge True productivity value Values in knowledgebase [R1.a] - Interval of possible - productivity values Resources - Compensation value - Reported productivity of - opponent Prediction of opponent’s Belief [R.1b] - behavior (B) Prefer ference ces Maximizing the compensation Profit maximization [R2] (C) Reaso asoning strategy Report with highest expected Best expected individual utility [R3] individual payment (D) Experie rience ce collect ction Value of strategies Implicit experience collection[R4.a] - History about past Explicit experience collection [R4.b] - experience (E) E Exploration strategy Random report Random exploration [R5.a] - Systematic exploration of Systematic exploration [R5.b] - under-, overestimation, and truthful reporting (F) Pay ayoff ff Incentive scheme defines Positive payoff [R6] positive payments only. 25

Behavior models Behavior Model Learning Algorithm Knowledge base Random Zero Intelligence #,# → report BehM1 Sarin Vahid #,# → report BehM2 Sarin Vahid productivity, # → report BehM3 Ficticious Play productivity, prediction → report Rational - - 26

Behavior models Behavior Model Learning Algorithm Knowledge base Random Zero Intelligence #,# → report BehM1 Sarin Vahid #,# → report BehM2 Sarin Vahid productivity, # → report BehM3 Ficticious Play productivity, prediction → report Rational - - 27

Results under varying incentives Effect of adapted incentives 28

Perspect ctive ives s on agent-base sed sim imula lation ion and it its contr tribu ibution tion  Analyzing Emergence  Incorporating human behavior  How to understand human behavior?  How to model human behavior? Usin ing artif ific icia ial l agents 29

The variety of agents… • Agent may vary from very simple condition-action patterns to complex, intelligents entities. Agent as „Softbot“ Robot without a body 30

Artif ific icia ial l Intellige lligence ce Russel and Norvig 2009, p.2 31

Agents s may fin ind good solu lutions! ions! 32

Agents s may fin ind good solu lutions! ions! 33

Perspect ctive ives s on agent-base sed sim imula lation ion and it its contr tribu ibution tion  Analyzing Emergence  Incorporating human behavior  How to understand human behavior?  How to model human behavior?  Using artificial agents 34

Finally… Incorporate human behavior in your models: „…this complexity exists, if you wish it away or not!" (Ken, in a different context) Reader: ;-) 35