ECoMASS 2013

ECoMASS Workshop: Call for Papers

Evolutionary computation (EC) and multi-agent systems and simulation (MASS) both involve populations of agents. EC is a learning technique by which a population of individual agents adapt according to the selection pressures exerted by an environment; MASS seeks to understand how to coordinate the actions of a population of (possibly selfish) autonomous agents that share an environment so that some outcome is achieved. Both EC and MASS have top-down and bottom up features. For example, some aspects of multi-agent system engineering (e.g., mechanism design) are concerned with how top-down structure can constrain or influence individual decisions. Similarly, most work in EC is concerned with how to engineer selective pressures to drive the evolution of individual behavior towards some desired goal. Multi-agent simulation (also called agent-based modeling) addresses the bottom-up issue of how collective behavior emerges from individual action. Likewise, the study of evolutionary dynamics within EC (for example in coevolution) often considers how population-level phenomena emerge from individual-level interactions. Thus, at a high level, we may view EC and MASS as examining and utilizing analogous processes. It is therefore natural to consider how knowledge gained within EC may be relevant to MASS, and vice versa; indeed, applications and techniques from one field have often made use of technologies and algorithms from the other field. Studying EC and MASS in combination is warranted and has the potential to contribute to both fields.

The EcoMASS workshop, now in its 7th iteration, welcomes original submissions on all aspects of Evolutionary Computation and Multi-Agent Systems and Simulation, which include (but are not limited to) the following topics and themes:

• Multi-agent systems and agent-based models utilizing evolutionary computation
• Optimization of multi-agent systems and agent-based models using evolutionary computation
• Evolutionary computation models which rely not on explicit fitness functions but rather implicit fitness functions defined by the relationship to other individuals/agents
• Applications utilizing MASS and EC in combination
• Biological agent-based models (usually called individual-based models) involving evolution
• Evolution of cooperation and altruism
• Genotypic representation of the complex phenotypic strategies of MASS
• Evolutionary learning within MASS (including Baldwinian learning and phenotypic plasticity)
• Emergence and feedbacks
• Open-ended strategy spaces and evolution
• Adaptive individuals within evolving populations

Paper Submission

Each accepted paper will be presented orally at the workshop and distributed in the workshop proceedings to all GECCO attendees. Authors should follow the format of the GECCO manuscript style; refer to http://www.sigevo.org/gecco-2013/papers.html for details. Manuscripts should not exceed 8 pages. Papers should be submitted by March 28, 2013 in PDF format to forrest.stonedahl@centre.edu with "ECoMASS paper submission" in the subject line.

Important Dates

Paper submission deadline: March 28, 2013 (passed)

Notification of acceptance: April 15, 2013 (passed)

Camera-ready deadline: April 25, 2013 (passed)

Accepted Author Registration deadline: (passed)

ECo-MASS 2013 Workshop Schedule

Date: July 7, 2013

Time: 14:00-18:00

Location: Amsterdam, The Netherlands, Room; 06A00

Schedule of Presentations

Program Committee

Workshop Chairs

• Bill Rand, University of Maryland
• Forrest Stonedahl, Centre College

Program Committee for ECoMASS 2013

• Mitchell Colby, Oregon State University
• Matt Knudson, Carnegie Mellon University
• Rinde van Lon, KU Leuven
• Michael North, Argonne National Laboratory
• Jim Reggia, University of Maryland
• Robert G. Reynolds, Wayne State University
• Rick Riolo, University of Michigan
• Moshe Sipper, Ben-Gurion University
• Logan Yliniemi, Oregon State University
• Tina Yu, Memorial University of Newfoundland

Former Program Committee Members

• Liviu Panait, Google
• Kagan Tumer, Oregon State University

Former ECoMASS Chairs

• Rick Riolo, University of Michigan
• Sevan G. Ficici, Natural Selection

Bill's Impertinent Recap of ECoMASS 2013

•Bill abused his power and gave a talk on his own work (absolute power corrupts absolutely)

•Deborah discussed why selling succotash is an emergent phenomenon (a rising tide…)

•Corrado told us that pheromones, though good for ants, are bad for detecting group identity (if it smells like a group…)

•Alan claimed that Homer Simpson has a small brain because he doesn’t like other people (doh!)

•Chris said that its good to have eyes all over your head none of which see very well (otherwise you get scared)

•David stated that short lived individuals who reproduce wildly do the best (only the good die young)

•Sabrina declared that our mobile phones may someday save our lives (of course, they will still frequently drop calls)

•Joshua asked how do we make our future robot overlords robust to errors (and do we want to?)

•Graham enlightened us as to why authors actually need to be inspired to create new genres (see Borges’ The Library of Babel)

Related Posters and Papers at GECCO 2013

Posters

•Partitioning Agents and Shaping Their Evaluation Functions in Air Traffic Problems with Hard Constraints, William John Curran; Adrian Agogino; Kagan Tumer

•A Multi-agent Genetic Algorithm for Resource-Constrained Project Scheduling Problems, xiaoxiao Yuan; Jing Liu

•Using Reinforcement Learning and Artificial Evolution for the Detection of Group Identities in Complex Adaptive Artificial Societies, Corrado Grappiolo; Julian Togelius; Georgios N. Yannakakis

•Sonification of Population Behavior in Particle Swarm Optimization, Tiago Fernandes Tavares; Alan Godoy

Monday

11:30: Evolving Multimodal Controllers with HyperNEAT, Justin K. Pugh, Kenneth O. Stanley

14:45: Hybrid POMDP based Evolutionary Adaptive Framework for Efficient Visual Tracking Algorithms, Yan Shen, Sarang Khim, WonJun Sung, Minhaz Uddin Ahmed, Phill Kyu Rhee

15:10: Controlling Tensegrity Robots through Evolution, Atil Iscen, Adrian Agogino, Vytas SunSpiral, Kagan Tumer

15:10: Neuroevolution Results in Emergence of Short-Term Memory in Multigoal Environment, Konstantin Lakhman, Mikhail Burtsev

16:30: Evolving Large-scale Neural Networks for Visual Reinforcement Learning, Jan Koutník, Giuseppe Cuccu, Juergen Schmidhuber, Faustino Gomez

Tuesday

•10:40: Testing Of Precision Agricultural Networks for Adversary-induced Problems, Karel Paul Bergmann, Jörg Denzinger

•11:55: On the impact of streaming interface heuristics on GP trading agents: An FX benchmarking study. Alexander Loginov, Malcolm Heywood

•14:20: Rolling Horizon Evolution versus Tree Search for Single-Player Real-Time Games, Diego Perez, Spyridon Samothrakis, Simon Lucas, Philipp Rohlfshagen

•14:20: Critical Interplay Density-dependent Predation and Evolution of the Social Herd, Randy Olson, David B. Knoester, Chris Adami

•15:10: Geometric-Based Sampling For Permutation Optimization, Olivier Regnier-Coudert, John McCall, Mayowa Ayodele

•17:20: Synergy in Ant Foraging Strategies: Memory and Communication Alone and in Combination, Kenneth Letendre, Melanie E. Moses

Wednesday

•11:05: A Bayesian Approach for Constrained Multi-Agent Minimum Time Search in Uncertain Dynamic Domains. Pablo Lanillos, Javier YañezZuluaga, Eva Besada-Portas

•11:05: An Evolutionary Multi-Agent System for Database Query Optimization. Frederico Augusto de Cezar Almeida Gonçalves, Frederico Gadelha Guimarães, Marcone Jamilson Freitas Souza

Previous ECoMASS Workshop Websites

• Currently unavailable...