GECCO 2022 will have a number of competitions ranging from different types of optimization problems to games and industrial problems. If you are interested in a particular competition, please follow the links to their respective web pages (see list below).
In addition to the competitions listed on this page, GECCO also hosts the Humies Award for human-competitive results produced by genetic and evolutionary computation.
After logging into GECCO's submission site https://ssl.linklings.net/conferences/gecco/, click on "Make a new submission", then selection "Competition Entry", and then select the respective competition.
Note that not all competitions offer this (if in doubt, please check with the respective competition organisers). The submission is (in general) voluntary, except when explicitly made mandatory by a competition.
|AbstractSwarm Multi-Agent Logistics Competition|
|Competition on Real Parameter Single Objective Bound Constrained Optimization|
|Dynamic Stacking Optimization in Uncertain Environments|
|Evolutionary Computation in the Energy Domain: Risk-based Energy Scheduling|
|Evolutionary Submodular Optimisation|
|Interpretable Symbolic Regression for Data Science|
|Minecraft Open-Endedness Challenge|
|Open Optimization Competition 2022: Better Benchmarking of Sampling-Based Optimization Algorithms|
|Optimization of a simulation model for a capacity and resource planning task for hospitals under special consideration of the COVID-19 pandemic|
|SpOC: Space Optimisation Competition|
AbstractSwarm Multi-Agent Logistics Competition
This competition aims to motivate work in the broad field of logistics. We have prepared a benchmarking framework which allows the development of multi-agent swarms to process a variety of test environments. Those can be extremely diverse, highly dynamic and variable of size. The ultimate goal of this competition is to foster comparability of multi-agent systems in logistics-related problems (e. g., in hospital logistics). Many such problems have good accessibility and are easy to comprehend, but hard to solve. Problems of different diffculty have been designed to make the framework interesting for educational purposes. However, finding effcient solutions for different a priori unknown test environments remains a challenging task for practitioners and researchers alike.
Following these ideas, in the AbstractSwarm Multi-Agent Logistics Competition, participants must develop agents that are able to cooperatively solve different a priori unknown logistics problems. A logistics problem is given as a graph containing agents and stations. An agent can interact with the graph (1) by deciding which station to visit next, (2) by communicating with other agents, and (3) by retrieving a reward for its previous decision. While simulating a scenario, a timetable in the form of a Gantt-chart is created according to the decisions of all agents. Submissions will be ranked according to the total number of idle time of all agents in several different a priori unknown problem scenarios in conjunction with the number of iterations needed to come to the solution.
Daan Apeldoorn primarily works for the Institute for Medical Biostatistics, Epidemiology and Informatics (IMBEI) in the Medical Informatics department at the University Medical Centre of the Johannes Gutenberg University Mainz, Germany, and additionally for the Z Quadrat GmbH in Mainz. His research focuses on the extraction and exploitation of knowledge bases in the context of learning agents. He is also active in the field of multi-agent systems with application in (hospital) logistics. In the past, he worked as a scientific staff member at the TU Dortmund University and the University of Koblenz-Landau.
Alexander Dockhorn is post-doctoral research associate at the Otto von Guericke University of Magdeburg. He received his PhD at the Otto von Guericke University in Magdeburg in 2020, after which he continued his research on games at the Game AI Lab of the Queen Mary University of London. His research focuses on forward model learning methods and the analysis of prediction-based search agents in games with a special interest in partial-information games. He is active member of the IEEE in which he serves as the chair of the IEEE CIS Competitions Sub-Committee and member of the Games Technical Committee (GTC). Since 2017, he is organizing the Hearthstone AI competition to foster comparability of AI agents in card games.
Lars Hadidi is a theoretical physicist working as a research fellow at the Institute for Medical Biostatistics, Epidemiology and Informatics (IMBEI) in the Medical Informatics department at the University Medical Centre of the Johannes Gutenberg University Mainz, Germany. He is currently focusing on neural networks which directly operate on graph structured data, their methods and applications.
Torsten Panholzer is managing director of the division Medical Informatics at the Institute for Medical Biostatistics, Epidemiology and Informatics (IMBEI) at the University Medical Centre Mainz, Germany. He studied natural sciences and graduated as PhD at the Johannes Gutenberg University Mainz. His research focus is on system and data integration, identity management and artificial intelligence.
Competition on Real Parameter Single Objective Bound Constrained Optimization
The goals are to evaluate the current state of the art in single objective numerical optimization with bound constraints with an increased number of maximum function evaluations. In the past, a maximum number of function evaluations did not scale with increasing dimensions while the complexity of the problems increased exponentially with the increasing dimensions. In addition, we will also consider several transformations such as translation, rotation, shearing, etc. in order to highlight the importance of these transformations. Although there are 100s of newly proposed metaheuristics in recent years, most have been evaluated on classical problems without rotation and with the global solution at the origin or very near the origin. We anticipate that this benchmark will help identify metaheuristics with various built-in biases to solve the classical problems effectively. In addition, we will also propose a novel scoring method to compare the algorithms.
Ponnuthurai Nagaratnam Suganthan is/was an associate editor of the Applied Soft Computing (Elsevier, 2018-), Neurocomputing (Elsevier, 2018-), IEEE Trans on Cybernetics (2012 - 2018), IEEE Trans on Evolutionary Computation (2005 - ), IEEE Trans on SMC: Systems (2020 - ), Information Sciences (Elsevier, 2009 - ), Pattern Recognition (Elsevier, 2001 - ) and Neurocomputing (2018 - ) Journals. He is a founding co-editor-in-chief of Swarm and Evolutionary Computation (2010 - ), an SCI Indexed Elsevier Journal. His research interests include swarm and evolutionary algorithms, pattern recognition, big data, deep learning and applications of swarm, evolutionary & machine learning algorithms. He was selected as one of the highly cited researchers by Thomson Reuters yearly from 2015 to 2020 in computer science. He served as the General Chair of the IEEE SSCI 2013. He has been a member of the IEEE (S'91, M'92, SM'00, F'15) since 1991 and an elected AdCom member of the IEEE Computational Intelligence Society (CIS) in 2014-2016. He is an IEEE CIS distinguished lecturer (DLP) in 2018-2021.
ALI WAGDY MOHAMED received his B.Sc., M.Sc. and PhD. degrees from Cairo University, in 2000, 2004 and 2010, respectively. Ali Wagdy is an Associate Professor at Operations Research department, Faculty of Graduate Studies for Statistical Research), Cairo University, Egypt. He was an Associate Professor of Statistics at Wireless Intelligent Networks Center (WINC), Faculty of Engineering and Applied Sciences, Nile University (2019-2021). Currently, I am an Associate Prof. with Mathematics and Actuarial Science Department, School of Sciences and Engineering, The American University in Cairo, Cairo, Egypt. Recently, He has been appointed as a member of the Education and Scientific Research Policy Council, Academy of Scientific Research (2021-2024). Recently, he has been recognized among the top 2% scientists according to Stanford University report 2019 and 2020, Respectively. He serves as reviewer of more than 80 international accredited top-tier journals and has been awarded the Publons Peer Review Awards 2018, for placing in the top 1% of reviewers worldwide in assorted field. He is an associate editor with Swarm and Evolutionary Computation Journal, Elsevier.
Kenneth V. Price
Kenneth V. Price earned his B.Sc. in physics from Rensselaer Polytechnic Institute in 1974. He briefly worked as a supervisor at the Teledyne-Gurley Scientific Instrument Company in Troy, New York before moving to San Francisco. He currently resides in Vacaville, California. An avid hobbyist, he is self-taught in the field of evolutionary computation. In 1994, he published an early ensemble annealing, threshold accepting algorithm (""genetic annealing""), which led Dr. R. Storn to challenge him to solve the Chebyshev polynomial fitting problem. Ken’s discovery of differential mutation proved to be the key to solving not only the Chebyshev polynomial fitting problem, but also many other difficult numerical global optimization problems. He is co-author of both the seminal paper on the differential evolution algorithm and the book “Differential Evolution: A practical approach to global optimization”. In 2017, Ken was awarded the IEEE CIS Pioneer Award for his seminal work on the differential evolution algorithm. Ken has also authored or co-authored seven additional peer-reviewed papers, contributed chapters to three books on optimization and has served as a reviewer for twelve different journals.
Anas A. Hadi is an Assistant Professor at Computer Science department at the Faculty of Computing and Information Technology, King Abdul-Aziz University (KAU). He received his M.Sc. and Phd degrees from computer science, KAU, 2013 and 2019, respectively. His current research interests include Machine Learning, Optimization, Brain-computer interface BCI, Feature selection. He has Obtained Rank 3 in CEC’17 competition on single objective bound constrained real-parameter numerical optimization in Proc of IEEE Congress on Evolutionary Computation, IEEE-CEC 2017, San Sebastián, Spain. Besides, Obtained Rank 3 and Rank 2 in CEC’18 competition on single objective bound constrained real-parameter numerical optimization and Competition on Large scale global optimization, in Proc of IEEE Congress on Evolutionary Computation, IEEE-CEC 2017, Sao Paolo, Brazil. Besides, Obtained Rank Rank 2 in CEC’20 competition on single objective bound constrained real-parameter numerical optimization, in Proc of IEEE Congress on Evolutionary Computation, IEEE-CEC 2020, Glasgow, UK. He published more than 20 papers in reputed and high-impact journals like Complex and Intelligent Systems, Swarm and Evolutionary Computation, and International Journal of Machine Learning and Cybernetics.
Abhishek Kumar received the B.Tech degree in Electrical Engineering from Uttarakhand Technical University, Dehradun in 2013. He finished his Ph.D. in Systems Engineering at the Department of Electrical Engineering, Indian Institute of Technology (BHU), Varanasi, India in 2019. He is the recipient of the “Young Researcher Award-2016” from the IEEE CIS Chapter, UP section, IIT Kanpur. His co-authored works “EBOwithCMAR” and “SASS” secured the first position in IEEE CEC-2017 special session and competition on bound-constrained optimization and the IEEE CEC-2020/GECCO-2020 special session and competition on real-world constrained optimization, respectively. His current research interests include swarm and evolutionary computation and its application in real-world optimization problems especially in Power System Optimization applications, optimization algorithms, and machine learning. He also serves as a reviewer for several journals including IEEE TCYB, IET GTD, SWEVO, and ASOC.
Dynamic Stacking Optimization in Uncertain Environments
Stacking problems are central to multiple billion-dollar industries. The container shipping industry needs to stack millions of containers every year. In the steel industry the stacking of steel slabs, blooms, and coils needs to be carried out efficiently, affecting the quality of the final product. The immediate availability of data – thanks to the continuing digitalization of industrial production processes – makes the optimization of stacking problems in highly dynamic environments feasible.
There are two tracks in this competition, same as in the last competition.
In the first track a dynamic environment is provided that represents a simplified stacking scenario. Blocks arrive continuously at a fixed arrival location from which they have to be removed swiftly. If the arrival location is full, the arrival of additional blocks is not possible. To avoid such a state, there is a range of buffer stacks that may be used to store blocks. Each block has a due date before which it should be delivered to the customer. However, blocks may leave the system only when they become ready, i.e., some time after their arrival. To deliver a block it must be put on the handover stack – which must contain only a single block at any given time. There is a single crane that may move blocks from arrival to buffer, between buffers, and from buffer to handover. The optimization must control this crane in that it reacts to changes with a sequence of moves that are to be carried out. The control does not have all information about the world. A range of performance indicators will be used to determine the winner.
The second track represents another stacking scenario that is derived from real-world scenarios. It features two cranes and two different handovers. The cranes have a capacity of larger than one which represents an additional challenge for the solver. The solver may just provide the moves and the cranes will sort out the order in which these are performed (not optimal though) or the solver may optimize both the moves and the assignment and schedule of the cranes. In this scenario, not the arrival stack is the critical part, but the handover stacks and thus the downstream process must not run empty.
The dynamic environments are implemented in form of a realtime simulation which provides the necessary change events. The simulation runs in a separate process and publishes its world state and change events via message queuing (ZeroMQ), and also listens for crane orders. Thus, control algorithms may be implemented as standalone applications using a wide range of programming languages. Exchanged messages are encoded using protocol buffers – again libraries are available for a large range of programming languages. As in the 2021 competition a website will be used that participants can use to create experiment and test their solvers. In addition, the simulation models are available at GitHub for offline testing and development at https://github.com/dynstack/dynstack. We gladly accept pull requests for new starter kits, existing algorithms and approaches, as well as additions to the bibliography on works that have used the competition for scientific research.
Andreas Beham received his MSc in computer science in 2007 and his PhD in engineering sciences in 2019, both from Johannes Kepler University Linz, Austria. He works as assistant professor at the R&D facility at University of Applied Sciences Upper Austria, Hagenberg Campus and is leading several funded research projects. Dr. Beham is co-architect of the open source software environment HeuristicLab and member of the Heuristic and Evolutionary Algorithms Laboratory (HEAL) research group led by Dr. Affenzeller. He has published more than 80 documents indexed by SCOPUS and applied evolutionary algorithms, metaheuristics, mathematical optimization, data analysis, and simulation-based optimization in industrial research projects. His research interests include applying dynamic optimization problems, algorithm selection, and simulation-based optimization and innovization approaches in practical relevant projects.
Stefan Wagner received his MSc in computer science in 2004 and his PhD in technical sciences in 2009, both from Johannes Kepler University Linz, Austria. From 2005 to 2009 he worked as associate professor for software project engineering and since 2009 as full professor for complex software systems at the Campus Hagenberg of the University of Applied Sciences Upper Austria. From 2011 to 2018 he was also CEO of the FH OÖ IT GmbH, which is the IT service provider of the University of Applied Sciences Upper Austria. Dr. Wagner is one of the founders of the research group Heuristic and Evolutionary Algorithms Laboratory (HEAL) and is project manager and head architect of the open-source optimization environment HeuristicLab. He works as project manager and key researcher in several R&D projects on production and logistics optimization and his research interests are in the area of combinatorial optimization, evolutionary algorithms, computational intelligence, and parallel and distributed computing.
Sebastian Leitner (né Raggl) received his MSc in bioinformatics in 2014 from the University of Applied Sciences Upper Austria. He is currently pursuing his PhD at the Johannes Kepler University Linz, Austria. Since 2015 he is a member of the research group Heuristic and Evolutionary Algorithms Laboratory (HEAL) where he is working on several industrial research projects. He has focused on stacking problems in the steel industry for which he has acquired a lot of experience in the application domain, but also in the scientific state of the art.
Johannes Karder received his master's degree in software engineering in 2014 from the University of Applied Sciences Upper Austria and is a research associate in the Heuristic and Evolutionary Algorithms Laboratory at the Research Center Hagenberg. His research interests include algorithm theory and development, simulation-based optimization and optimization networks. He is a member of the HeuristicLab architects team. He is currently pursuing his PhD in technical sciences at the Johannes Kepler University, Linz, where he conducts research on the topic of dynamic optimization problems.
Bernhard Werth received his MSc in computer science in 2016 from Johannes Kepler University Linz, Austria. He works as a researcher at the R&D facility at University of Applied Sciences Upper Austria, Hagenberg Campus. Mr Werth is contributor to the open source software environment HeuristicLab and member of the Heuristic and Evolutionary Algorithms Laboratory (HEAL) research group led by Dr. Affenzeller. He has authored and co-authored several papers concerning evolutionary algorithms, fitness landscape analysis, surrogate-assisted optimization and data quality monitoring.
Evolutionary Computation in the Energy Domain: Risk-based Energy Scheduling
Following the success of the previous editions at IEEE PES; CEC; GECCO, WCCI, we are launching another challenging edition of competition at major conferences in the field of computational intelligence. This edition of GECCO 2022 competition proposes one track in the energy domain:
Track 1) Risk-based optimization of aggregators’ day-ahead energy resource management (ERM) considering uncertainty associated with the high penetration of distributed energy resources (DER). This test bed is constructed under the same framework of past competitions (therefore, former competitors can adapt their algorithms to this new track), representing a centralized day-ahead ERM in a smart grid with a 13-bus distribution network using a 150-scenario case study with 10 scenarios considering extreme events (high impact, and low probability). A conditional value-at-risk (CVaR) mechanism is used to measure the risk associated with the extreme events for a confidence level (α) of 95%. We also add some restrictions to the initialization of the initial solution and the allowed repairs and tweak-heuristics.
Note: The track is developed to run under the same framework of past competitions.
The GECCO 2022 competition on “Evolutionary Computation in the Energy Domain: Risk-based Energy Scheduling” has the purpose of bringing together and testing the more advanced Computational Intelligence (CI) techniques applied to energy domain problems, namely a risk-based optimal day-ahead ERM considering the uncertainty associated with high penetration of DER. The competition provides a coherent framework where participants and practitioners of CI can test their algorithms to solve a real-world optimization problem in the energy domain. The participants have the opportunity to evaluate if their algorithms can rank well in the proposed problem since we understand the validity of the “no-free lunch theorem”, making this contest a unique opportunity worth to explore the applicability of the developed approaches in a real-world problem beyond the typical benchmark and standardized CI problems.
João Soares has a B.Sc. in computer science (2008) and a master (2011) in Electrical Engineering by Polytechnic of Porto. He attained his Ph.D. degree in Electrical and Computer Engineering at UTAD university (2017). He is a researcher at ISEP/GECAD and his research interests include optimization in power and energy systems, including heuristic, hybrid and classical optimization.
Fernando Lezama received the Ph.D. in ICT from the ITESM, Mexico, in 2014. Since 2017, he is a researcher at GECAD, Polytechnic of Porto, where he contributes in the application of computational intelligence (CI) in the energy domain. Dr. Lezama is part of the National System of Researchers of Mexico since 2016, Chair of the IEEE CIS TF 3 on CI in the Energy Domain, and has been involved in the organization of special sessions, workshops, and competitions (at IEEE WCCI, IEEE CEC and ACM GECCO), to promote the use of CI to solve complex problems in the energy domain.
José Almeida has a degree in Electrical and Computer Engineering (2019) from Polytechnic Institute of Porto, Porto. He is currently working towards the M.Sc. degree in electrical engineering from the Polytechnic Institute of Porto (ISEP/IPP), Porto, Portugal. He is a Researcher with GECAD—Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development, ISEP/IPP. His research interests include optimization in power and energy systems; electric vehicles; smart grids; distributed energy resource management; and electricity markets.
Bruno Canizes received the M.Sc. degree in electrical engineering from the Polytechnic Institute of Porto (ISEP/IPP), Porto, Portugal, in 2010, and Ph.D. degree with the University of Salamanca, Salamanca, Spain, in 2019. He is a Researcher with GECAD—Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development, ISEP/IPP. His research interests include distribution network planning, operation, and reconfiguration; smart grids; electrical vehicles; distributed energy resource management; power system reliability; future power systems; optimization; electricity markets; and intelligent house management systems.
Zita Vale received the Ph.D. degree in electrical and computer engineering from the University of Porto, Porto, Portugal, in 1993. She is currently a Professor with the Polytechnic Institute of Porto, Porto. Her research interests focus on artificial intelligence applications, smart grids, electricity markets, demand response, electric vehicles, and renewable energy sources.
Evolutionary Submodular Optimisation
Submodular functions play a key role in the area of optimisation as they allow to model many real-world optimisation problem. Submodular functions model a wide range of problems where the benefit of adding solution components diminishes with the addition of elements. They form an important class of optimization problems, and are extensively studied in the literature. Problems that may be formulated in terms of submodular functions include influence maximization in social networks, maximum coverage, maximum cut in graphs, sensor placement problem, and sparse regression. In recent years, the design and analysis of evolutionary algorithms for submodular optimisation problems has gained increasing attention in the evolutionary computation and artificial intelligence community.
The aim of the competition is to provide a platform for researchers working evolutionary computing methods and interested in benchmarking them on a wide class of combinatorial optimization problems.
The competition will benchmark evolutionary computing techniques for submodular optimisation problems and enable performance comparison for this type of problems. It provides an idea vehicle for researchers and students to design new algorithms and/or benchmark their existing approaches on a wide class of combinatorial optimization problems captured by submodular functions.
The description of the benchmark and evaluation process will be available on the competition webpage (by latest 15 April 2022).
Aneta Neumann graduated in Computer Science from the Christian-Albrechts-University of Kiel, Germany and received her PhD from the University of Adelaide, Australia. She is currently a postdoctoral researcher at the School of Computer Science, The University of Adelaide, Australia. She has recently participated in artistic exhibition SALA 2016-17 and 2020 in Adelaide. She presented invited talks at UCL London, Goldsmiths, University of London, University of Nottingham, University of Sheffield, Hasso Plattner Institut University of Potsdam, Sorbonne University, University of Melbourne, University of Sydney in 2016-19. She received the Lorentz Center Grant 2020, Optimization Meets Machine Learning, Leiden, The Netherlands, the ACM Women scholarship, sponsored by Google, Microsoft, and Oracle, the Hans-Juergen and Marianna Ohff Research Grant in 2018, and the Best Paper Nomination at GECCO 2019 in the track “Genetic Algorithms”. She is a co-designer and co-lecturer for the EdX Big Data Fundamentals course in the Big Data MicroMasters® program and Online Pearson Education, Working with Big Data. Her main research interest focuses on bio-inspired computation, particularly dynamic and stochastic optimization, evolutionary diversity optimization and digital art. She serves as the co-chair of the Real-World Applications track at GECCO 2021and GECCO 2022.
Frank Neumann is a professor and the leader of the Optimisation and Logistics group at the University of Adelaide and an Honorary Professorial Fellow at the University of Melbourne. His current position is funded by the Australian Research Council through a Future Fellowship and focuses on AI-based optimisation methods for problems with stochastic constraints. Frank has been the general chair of the ACM GECCO 2016 and co-organised ACM FOGA 2013 in Adelaide. He is an Associate Editor of the journals "Evolutionary Computation" (MIT Press) and ACM Transactions on Evolutionary Learning and Optimization. In his work, he considers algorithmic approaches in particular for combinatorial and multi-objective optimization problems and focuses on theoretical aspects of evolutionary computation as well as high impact applications in the areas of cybersecurity, renewable energy, logistics, and mining.
Chao Qian is an Associate Professor in the School of Artificial Intelligence, Nanjing University, China. He received the BSc and PhD degrees in the Department of Computer Science and Technology from Nanjing University. After finishing his PhD in 2015, he became an Associate Researcher in the School of Computer Science and Technology, University of Science and Technology of China, until 2019, when he returned to Nanjing University.
His research interests are mainly theoretical analysis of evolutionary algorithms and designing evolutionary algorithms with provable approximation guarantee for sophisticated optimization problems, particularly in machine learning. He has published one book “Evolutionary Learning: Advances in Theories and Algorithms” and more than 30 papers in top-tier journals (e.g., AIJ, TEvC, ECJ, Algorithmica, TCS) and conferences (e.g., AAAI, IJCAI, NIPS). He has won the ACM GECCO 2011 Best Theory Paper Award, the IDEAL 2016 Best Paper Award, and the IEEE CEC 2021 Best Student Paper Award Nomination. He is an editorial board member of the Memetic Computing journal. He is a member of Evolutionary Computation Technical Committee, and the chair of IEEE Computational Intelligence Society (CIS) Task Force on Theoretical Foundations of Bio-inspired Computation.
Interpretable Symbolic Regression for Data Science
Symbolic regression methods have made tremendous advances in the past decade, and have recently gained interest as the broader scientific community has recognized the importance of interpretable machine learning. Despite this, there is little agreement in the field about which algorithms are “state-of-the-art”, and how to best design symbolic regression methods for use in the real world. This competition seeks to distill algorithmic design choices and improve the practice of symbolic regression by evaluating the submitted symbolic regression methods on previously unseen, real-world and synthetic datasets. These datasets will be sourced mainly from the domains of physics, epidemiology and bioinformatics.
Participants are asked to adapt and submit their symbolic regression algorithms to SRBench, following the contributing guidelines. SRBench will automatically test these methods for conformance with the competition.
After the submission deadline, methods will be tested on previously unseen datasets. These datasets cover synthetic and real-world problems, and in each case, either an exact model or a human-designed model will be used for comparison. Notice that these will be new benchmarks specifically curated for this competition. The current version of SRBench will serve as a first-pass filter for candidate entries. As such, participants are free to test and fine-tune their algorithms on the current version of SRBench. Algorithm submissions will be judged by their ability to discover the ground-truth models, or, in the case of real-world data, approximate or outperform the expert models with similar or lower complexity. Winners will be determined based on the accuracy and simplicity of the generated models, both individually and in the Pareto efficient sense. After competition, the submitted methods, evaluation procedure, and new datasets will be made publicly available.
William La Cava
William La Cava is a faculty member in the Computational Health Informatics Program (CHIP) at Boston Children’s Hospital and Harvard Medical School. He received his PhD from UMass Amherst with a focus on interpretable modeling of dynamical systems. Prior to joining CHIP, he was a post-doctoral fellow and research associate in the Institute for Biomedical Informatics at the University of Pennsylvania.
Marco Virgolin is a junior researcher at Centrum Wiskunde & Informatica (CWI), the Dutch national center of mathematics and computer science. He received his PhD from Delft University of Technology. Marco works on explainable AI, most notably by means of evolutionary machine learning methods such as genetic programming. He is also interested in medical applications of machine learning and human-machine interaction.
Fabricio Olivetti de França
Fabricio Olivetti de França is an associated professor in the Center for Mathematics, Computing and Cognition (CMCC) at Federal University of ABC. He received his PhD in Computer and Electrical Engineering from State University of Campinas. His current research topics are Symbolic Regression, Evolutionary Computation and Functional Data Structures.
Michael Kommenda is a senior researcher and project manager at the University of Applied Sciences Upper Austria, where he leads several applied research projects with a focus on machine learning and data-based modeling. He received his PhD in technical sciences in 2018 from the Johannes Kepler University Linz, Austria. The title of his dissertation is Local Optimization and Complexity Control for Symbolic Regression, which condenses his research on symbolic regression so far. Michael's research interests currently are improving symbolic regression so that it becomes an established regression and machine learning technique. Additionally, Michael is one of the architects of the HeuristicLab optimization framework and contributed significantly to its genetic programming and symbolic regression implementation.
Maimuna (Maia) Majumder, MPH, PhD is a faculty member in the Computational Health Informatics Program (CHIP) at Harvard Medical School and Boston Children's Hospital. Prior to joining CHIP, she received her PhD from the Institute for Data, Systems, and Society at the Massachusetts Institute of Technology. Her research interests involve the application of artificial intelligence approaches to public health problems, with a focus on emerging epidemics and digital data streams.
Minecraft Open-Endedness Challenge
The purpose of the second contest on open-endedness is to highlight the progress in algorithms that can create novel and increasingly complex artefacts. While most experiments in open-ended evolution have so far focused on simple toy domains, we believe Minecraft -with its almost unlimited possibilities- is the perfect environment to study and compare such approaches. While other popular Minecraft competitions, like MineRL, have an agent-centric focus, in this competition the goal is to directly evolve Minecraft builds.
As part of this competition, we introduce the EvoCraft API. EvoCraft is implemented as a mod for Minecraft that allows clients to manipulate blocks in a running Minecraft server programmatically through an API. The framework is specifically developed to facilitate experiments in artificial evolution. The competition framework also supports the recently added "redstone" circuit components in Minecraft, which allowed players to build amazing functional structures, such as bridge builders, battle robots, or even complete CPUs. Can an open-ended algorithm running in Minecraft discover similarly complex artefacts automatically?
In addition to the general Open-Ended competition, we will add an Open-Ended Play track. With this track, we would like to encourage research that leads to new and surprising Minecraft machines, that more directly make use of the unique Minecraft physics. Here agents must build Minecraft machines to score a goal against their opponent, which must build machines to counter it, while simultaneously trying to score their own goal, all with a limited budget of blocks.
Postdoc at IT University of Copenhagen, researching safety in reinforcement learning, self-driving vehicles and artificial life. Did his PhD at the University of Geneva in Switzerland specializing in bioinformatics, genetic algorithms and machine learning applied to studies in evolutionary biology.
Rasmus Berg Palm
Postdoc at IT University of Copenhagen, researching unsupervised learning of object oriented world models. Did his PhD at the Technical University of Denmark in end-to-end document understanding.
Research Assistant at the Robotics, Evolution, and Art Lab (REAL), IT University of Copenhagen. Working on meta-learning, evolutionary computation and open-endedness.
Professor at the IT University of Copenhagen where he co-directs the Robotics, Evolution and Art Lab (REAL). He is currently the principal investigator of a Sapere Aude: DFF Starting Grant (Innate: Adaptive Machines for Industrial Automation). He has won several international scientific awards, including multiple best paper awards, the Distinguished Young Investigator in Artificial Life 2018 award, a Google Faculty Research Award in 2019, and an Amazon Research Award in 2020. More information: sebastianrisi.com
Open Optimization Competition 2022: Better Benchmarking of Sampling-Based Optimization Algorithms
Our Nevergrad and IOHprofiler environments aim at building and establishing open-source, user-friendly, and community-driven platforms for comparing different optimization techniques.
The goal of this competition is to make benchmarking even more accessible, reproducible and fairer. All submissions that contribute towards these goals are most welcome!
There is no restriction on what to submit. All submissions that contribute to building and establishing open-source, user-friendly, and community-driven platforms for comparing different optimization techniques are welcome. Typical submissions fall into one of these categories: new benchmark problems, additional performance measures or statistics, visualization of benchmark data, extending or improving the functionalities of our benchmarking environments, interfaces to other existing benchmarking platforms, etc.
Your creativity is the only limit ;-)
Carola Doerr, formerly Winzen, is a permanent CNRS researcher at Sorbonne University in Paris, France. Carola's main research activities are in the analysis of black-box optimization algorithms, both by mathematical and by empirical means. Carola is regularly involved in the organization of events around evolutionary computation and related topics, for example as program chair for PPSN 2020, FOGA 2019 and the theory tracks of GECCO 2015 and 2017, as guest editor for IEEE Transactions on Evolutionary Computation and Algorithmica, as organizer of Dagstuhl seminars and Lorentz Center workshops. Carola is an associate editor of ACM Transactions on Evolutionary Learning and Optimization (TELO) and board member of the Evolutionary Computation journal. Her works have received several awards, among them the Otto Hahn Medal of the Max Planck Society, best paper awards at EvoApplications and CEC, and four best paper awards at GECCO.
Olivier Teytaud is research scientist at Facebook. He has been working in numerical optimization in many real-world contexts - scheduling in power systems, in water management, hyperparameter optimization for computer vision and natural language processing, parameter optimization in reinforcement learning. He is currently maintainer of the open source derivative free optimization platform of Facebook AI Research (https://github.com/facebookresearch/nevergrad), containing various flavors of evolution strategies, Bayesian optimization, sequential quadratic programming, Cobyla, Nelder-Mead, differential evolution, particle swarm optimization, and a platform of testbeds including games, reinforcement learning, hyperparameter tuning and real-world engineering problems.
Jérémy Rapin is a research engineer at Facebook. He has been working on signal processing, optimization and deep learning, mostly in the domain of medical imaging. His current focus is on developing nevergrad, an open- source derivative-free optimization platform.
Thomas Bäck is Full Professor of Computer Science at the Leiden Institute of Advanced Computer Science (LIACS), Leiden University, The Netherlands, where he is head of the Natural Computing group since 2002. He received his PhD (adviser: Hans-Paul Schwefel) in computer science from Dortmund University, Germany, in 1994, and then worked for the Informatik Centrum Dortmund (ICD) as department leader of the Center for Applied Systems Analysis. From 2000 - 2009, Thomas was Managing Director of NuTech Solutions GmbH and CTO of NuTech Solutions, Inc. He gained ample experience in solving real-life problems in optimization and data mining through working with global enterprises such as BMW, Beiersdorf, Daimler, Ford, Honda, and many others. Thomas Bäck has more than 350 publications on natural computing, as well as two books on evolutionary algorithms: Evolutionary Algorithms in Theory and Practice (1996), Contemporary Evolution Strategies (2013). He is co-editor of the Handbook of Evolutionary Computation, and most recently, the Handbook of Natural Computing. He is also editorial board member and associate editor of a number of journals on evolutionary and natural computing. Thomas received the best dissertation award from the German Society of Computer Science (Gesellschaft für Informatik, GI) in 1995 and the IEEE Computational Intelligence Society Evolutionary Computation Pioneer Award in 2015.
Hao Wangobtained his PhD (cum laude) from Leiden University in2018. He is currently employed as an assistant professor of computer science at Leiden University. Previously, he has a research stay at Sorbonne University, France. He received the Best Paper Award at the PPSN2016conference and was a best paper award finalist at the IEEE SMC 2017 conference. His research interests are in the analysis and improvement of efficient global optimization for mixed-continuous search spaces, Evolution strategies, Bayesian optimization, and benchmarking.
Diederick Vermetten is a PhD student at LIACS. He is part of the core development team of IOHprofiler, with a focus on the IOHanalyzer. His research interests include benchmarking of optimization heuristics, dynamic algorithm selection and configuration as well as hyperparameter optimization.
Optimization of a simulation model for a capacity and resource planning task for hospitals under special consideration of the COVID-19 pandemic
Similar to the many previous competitions, the team of the Institute of Data Science, Engineering, and Analytics at the TH Cologne (IDE+A), hosts the 'Industrial Challenge' at the GECCO 2022.
Based on the 2021 GECCO industrial challenge an updated more advanced problem is provided. This year’s industrial challenge is again in cooperation with an IDE+A partner from health industry and with Bartz & Bartz GmbH.
Simulation models are valuable tools for resource usage estimation and capacity planning. Your goal is to determine improved simulation model parameters for a capacity and resource planning task for hospitals. The simulator, babsim.hospital, explicitly covers difficulties for hospitals caused by the COVID-19 pandemic. The simulator can handle many aspects of resource planning in hospitals:
- various resources such as ICU beds, ventilators, personal protection equipment, staff, pharmaceuticals
- several cohorts (based on age, health status, etc.).
The task represents an instance of an expensive, high-dimensional computer simulation-based optimization problem and provides an easy evaluation interface that will be used for the setup of our challenge. The simulation will be executed through an interface and hosted on one of our servers (similar to our last year's challenge).
The task is to find an optimal parameter configuration for the babsim.hospital simulator with a very limited budget of objective function evaluations. The best-found objective function value counts. There will be multiple versions of the babsim.hospital simulations, with slightly differing optimization goals, so that algorithms can be developed and tested before they are submitted for the final evaluation in the challenge.
The participants will be free to apply one or multiple optimization algorithms of their choice.
Thus, we enable each participant to apply his/her algorithms to a real problem from health industry, without software setup or licensing that would usually be required when working on such problems.
M. Eng. Sowmya Chandrasekaran is a research associate at Institute for Data Science, Engineering and Analytics TH Köln, Germany. Her research interest includes: Artificial Intelligence, Anomaly Detection, Statistical Performance Analysis, Machine Learning, Deep Learning and Internet of Things.
Frederik is a Ph.D. student at the Institute of Data Science, Engineering, and Analytics at the CUAS (Cologne University of Applied Sciences). After earning his bachelor's degree in Electronics as well as a master's degree in Automation & IT, his research is now focused on the parallel application of surrogate model-based optimization.
- Academic Background: Ph.D. (Dr. rer. nat.), TU Dortmund University, 2005, Computer Science. * Professional Experience: Shareholder, Bartz & Bartz GmbH, Germany, 2014 – Present; Speaker, Research Center Computational Intelligence plus, Germany, 2012 – Present; Professor, Applied Mathematics, TH Köln, Germany, 2006 – Present. * Professional Interest: Computational Intelligence; Simulation; Optimization; Statistical Analysis; Applied Mathematics. * ACM Activities: Organizer of the GECCO Industrial Challenge, SIGEVO, 2011 – Present; Event Chair, Evolutionary Computation in Practice Track, SIGEVO, 2008 – Present; Tutorials Evolutionary Computation in Practice, SIGEVO, 2005 – 2013; GECCO Program Committee Member, Session Chair, SIGEVO, 2004 – Present. * Membership and Offices in Related Organizations: Program Chair, International Conference Parallel Problem Solving from Nature, Jozef Stefan Institute, Slovenia, 2014; Program Chair, International Workshop on Hybrid Metaheuristics, TU Dortmund University, 2006; Member, Special Interest Group Computational Intelligence, VDI/VDE-Gesellschaft für Mess- und Automatisierungstechnik, 2008 – Present. * Awards Received: Innovation Partner, State of North Rhine-Westphalia, Germany, 2013; One of the top 20 researchers in applied science by the Ministry of Innovation, Science and Research of the State of North Rhine-Westphalia, 2017.
SpOC: Space Optimisation Competition
SpOC (Space optimisation Competition) is a new optimisation competition proposed by the
Advanced concepts Team of the European Space Agency in the context of GECCO 2022. The
competition will have several teams of experts around the word compete to find the best solution to
multiple optimization problems applied to advanced space scenarios, with a focus on metaheuristics
and black-box optimization.
Several highly complex optimisation problems will be simultaneously released and submitted to the
scientific community who will have roughly one month to solve them. Participants will compete to
find the best solution for each individual problem, but also to be the best overall team. Similar to
multi-sport events, SpOC will award global points to the best performing teams for each problem.
These points will be used to establish a global ranking that will decide the winner of the competition.
In short, if GTOC is the America’s Cup of trajectory optimization, SpOC aims to be the Ironman race
of space optimization.
Each individual problem will be inspired by a promising advanced space concept and a global
inspiring context will be provided for the competition. All problems will differ in nature and
objective, so that a single solution approach should not be easily applicable to all of them, and be
complex enough to make for a challenging competition . The organizers may provide if needed a
The competition will be open to everybody worldwide. The target audience for the challenge is
experienced aerospace engineers and mathematicians but graduate students are also highly
encouraged to participate.
Emmanuel Blazquez graduated in Aerospace Engineering from the Institut Supérieur de l’Aéronautique et de l’Espace (ISAE-SUPAERO) in 2017 and pursued a second master in Space
Engineering at Politecnico di Milano graduating with a master thesis on GPU-accelerated N-body asteroid aggregation models. He was awarded a Ph.D. by the University of Toulouse Paul-Sabatier in 2021 for his work on rendezvous optimization and GNC design on cislunar near-rectilinear Halo orbits, which was the result of a collaboration between the European Space Agency, ISAE-SUPAERO and Airbus Defence and Space. Emmanuel recently joined the Advanced Concepts Team of ESA as a research fellow in advanced mission analysis with a focus on on-board real-time optimization asssisted by Artificial Intelligence. His research interests also include Autonomous Guidance and Control architectures, Multibody Astrodynamics and Global trajectory optimization.
Dr. Izzo graduated in Aeronautical Engineering from the University Sapienza of Rome in 1999 and later obtained a second master in “Satellite Platforms” at the University of Cranfield in the UK and a Ph.D. in Mathematical Modelling in 2003, at the University Sapienza of Rome. In 2004, he moved to the European Space Agency (ESA) in the Netherlands as a research fellow in Mission Analysis Dr. Izzo is now heading the Advanced Concepts Team and manageing its interface to the rest of ESA. During the years spent with tha ACT, he has led studies in interplanetary trajectory design and artificial intelligence and he took part in several other innovative researches on diverse fields. He started the Global Trajectory Optimization Competitions events, the ESA’s Summer of Code in Space, and the Kelvins competition platform (https://kelvins.esa.int/). Dr. Izzo has published more than 150 papers in journals, conferences and books. In GECCO 2013, he received the Humies Gold Medal for the work on grand tours of the galilean moons and, the following year, he won the 8th edition of the Global Trajectory Optimization Competition, organized by NASA/JPL, leading a mixed team of ESA/JAXA scientists. His interests range from computer science, open source software development, interplanetary trajectory optimization, biomimetics and artificial intelligence.
Dr.-Ing. Pablo Gómez received his M.Sc. in Computer science from the Technical University Munich in 2015. In 2019, he obtained a Ph.D. from the Friedrich-Alexander University Erlangen-Nürnberg and the University Hospital Erlangen, where he conducted research on machine learning and numerical methods for endoscopic videoprocessing and vocal fold dynamics. After working in industry research on machine learning methods for genomics, he joined the Advanced Concepts Team of the European Space Agency in 2020. His current research interests include machine learning, high performance computing and numerical methods.
Alexander Hadjiivanov started his academic journey in Japan with a BS in physics from Osaka University, followed by a MA in linguistics from Kyoto University. During his subsequent career as a professional science translator, he followed the development of cutting-edge research in various areas of artificial intelligence. Alexander returned to academia to obtain a PhD in artificial intelligence from the University of New South Wales in Australia, where he conducted research on natural language processing, neuroevolution and spiking neural networks. After a couple of fastpaced years as the Head of Research at a Sydney-based startup, Alexander joined ESA's Advanced Concepts Team as a research fellow in artificial intelligence. He is currently working on biologically inspired models of adaptive perception, self-organisation of neural activation patterns in spiking neural networks, spatiotemporal memory and axon guidance as a form of 'single-network' neuroevolution.
Marcus Märtens graduated from the University of Paderborn (Germany) with a Masters degree in computer science. He joined the European Space Agency as a Young Graduate Trainee in artificial intelligence where he worked on multi-objective optimization of spacecraft trajectories. He was part of the winning team of the 8th edition of the Global Trajectory Optimization Competition (GTOC) and received a HUMIES gold medal for developing algorithms achieving human competitive results in trajectory design. The Delft University of Technology awarded him a Ph.D. for his thesis on information propagation in complex networks. After his time at the network architectures and services group in Delft (Netherlands), Marcus rejoined the European Space Agency, where he works as a Research Fellow in the Advanced Concepts Team. While his main focus is on applied artificial intelligence and evolutionary optimization, Marcus has worked together with experts from different fields and authored works related to neuroscience, cyber-security and gaming.