Journal Articles
Stephen Kelly, Tatiana Voegerl, Wolfgang Banzhaf, and Cedric Gondro. Evolving Hierarchical Memory-Prediction Machines in Multi-Task Reinforcement Learning. Genetic Programming and Evolvable Machines, 2021. pdf
Stephen Kelly, Robert J. Smith, Malcolm I. Heywood, and Wolfgang Banzhaf. Emergent Tangled Program Graphs in Partially Observable Recursive Forecasting and ViZDoom Navigation Tasks. ACM Transactions on Evolutionary Learning and Optimization, 1(3), 2021 ACM
Stephen Kelly and Malcolm I. Heywood. Emergent Solutions to High-Dimensional Multi-Task Reinforcement Learning. Evolutionary Computation, 26(3):347-380, 2018. MIT Press. pdf
Silver placed at Human-Competitive (Humies) Competition
Stephen Kelly and Malcolm I. Heywood. Discovering Agent Behaviours through Code Reuse: Examples from Half-Field Offense and Ms. Pac-Man. IEEE Transactions on Games, 10(2):195–208, 2018. IEEE pdf
Book Chapters
Tanya Djavaherpour, Ali Naqvi, Eddie Zhuang, and Stephen Kelly. Evolving Many-Model Agents with Vector and Matrix Operations in Tangled Program Graphs. Genetic Programming Theory and Practice XXI, 2024. Springer (to appear)
Stephen Kelly and Jory Schossau. Evolutionary Computation and the Reinforcement Learning Problem. In: Banzhaf, W., Machado, P., Zhang, M. (eds) Handbook of Evolutionary Machine Learning. Genetic and Evolutionary Computation. 2024. Springer, Singapore. https://doi.org/10.1007/978-981-99-3814-8_4
Stephen Kelly and Wolfgang Banzhaf. Temporal Memory Sharing in Visual Reinforcement Learning. Genetic Programming Theory and Practice XVII, pages 101-119, 2020. Springer
Stephen Kelly, Robert Smith, and Malcolm I. Heywood. Emergent Policy Discovery for Visual Reinforcement Learning through Tangled Program Graphs: A Tutorial. Genetic Programming Theory and Practice XVI, pages 37-57, 2019. Springer
Conference Papers
Ali Naqvi and Stephen Kelly. Towards Evolving Creative Algorithms: Musical Time Series Forecasting with Tangled Program Graphs. Workshop on Evolution, Criticality and Creativity in Collective Intelligence (ECCCI), The 2024 Conference on Artificial Life (ALife 2024)
Maryam Akbari Moghaddam, Stephen Kelly, and Douglas Down. Demand Forecasting and Rebalancing in Bike Share Systems using Deep Learning and Evolutionary Computation. IEEE Intelligent Transportation Systems Society (ITSS), 2024. IEEE
Ethan Sequeira, Hussein Saad, Stephen Kelly, and Matthew Giamou. Towards Optimal Beacon Placement for Range-Aided Localization, Conference on Robots and Vision (CRV), 2024 arxiv Collaboration with ARCO LAB
Stephen Kelly, Daniel S. Park, Xingyou Song, Mitchell McIntire, Pranav Nashikkar, Ritam Guha, Wolfgang Banzhaf, Kalyanmoy Deb, Vishnu Naresh Boddeti, Jie Tan, Esteban Real. Discovering Adaptable Symbolic Algorithms from Scratch. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 3889-3896, 2023. IEEE. Finalist for Best Overall
Paper Award
Ritam Guha, Wei Ao, Stephen Kelly, Vishnu Boddeti, Erik Goodman, Wolfgang Banzhaf, and Kalyanmoy Deb. 2023. MOAZ: A Multi-Objective AutoML-Zero Framework. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO '23). Association for Computing Machinery, New York, NY, USA, 485–492. https://doi.org/10.1145/3583131.3590391 Collaboration with Human Analysis Lab
Rovere, G., Cuyabano, B.CD, Makanjuola, B., Kelly, S., Gondro, C. Phenotypic and Genetic Trends in American Angus Associated with Climate Variability. Proceedings of 12th World Congress on Genetics Applied to Livestock Production (WCGALP) Technical and species orientated innovations in animal breeding, and contribution of genetics to solving societal challenges. Pages 219-222. WAP 2022
Kenneth N. Reid, Iliya Miralavy, Stephen Kelly, Wolfgang Banzhaf, and Cedric Gondro. 2021. The factory must grow: automation in Factorio. In Proceedings of the Genetic and Evolutionary Computation Conference Companion (GECCO '21). Association for Computing Machinery, New York, NY, USA, 243–244. https://doi.org/10.1145/3449726.3459463
Stephen Kelly, Jacob Newsted, Wolfgang Banzhaf, and Cedric Gondro. A Modular Memory Framework for Time Series Prediction. In Proceedings of the 2020 Genetic and Evolutionary Computation Conference (GECCO '20), 2020
Stephen Kelly and Malcolm I. Heywood. Multi-Task Learning in Atari Video Games with Emergent Tangled Program Graphs. In Proceedings of the 2017 Genetic and Evolutionary Computation Conference (GECCO '17), 2017 pdf
Best Paper - DETA Track
Stephen Kelly and Malcolm I. Heywood. Emergent Tangled Graph Representations for Atari Game Playing Agents. In proceedings of the 20th European Conference on Genetic Programming, 2017 pdf
Best Paper - EuroGP
EuroGP 2017 presentation slides.
Video of champion TPG policy playing the game Frostbite.
Jessica P.C. Bonson, Stephen Kelly, Andrew R. McIntyre, and Malcolm I. Heywood. On Synergies between Diversity and Task Decomposition in Constructing Complex Systems with GP. In Proceedings of the 2016 Genetic and Evolutionary Computation Conference (GECCO '16), 2016 pdf
Robert J. Smith, Stephen Kelly, and Malcolm I. Heywood. Discovering Rubik's Cube Subgroups using Coevolutionary GP: A Five Twist Experiment. In Proceedings of the 2016 Genetic and Evolutionary Computation Conference (GECCO '16), 2016 pdf
Stephen Kelly and Malcolm I. Heywood. Knowledge Transfer from Keepaway Soccer to Half-field Offense through Program Symbiosis: Building Simple Programs for a Complex Task. In Proceedings of the 2015 Genetic and Evolutionary Computation Conference (GECCO '15), 2015 pdf
Stephen Kelly and Malcolm I. Heywood. Genotypic versus Behavioural Diversity for Teams of Programs Under the 4-v-3 Keepaway Soccer Task. In proceedings of the 28th AAAI Conference on Artificial Intelligence, 2014
Stephen Kelly and Malcolm I. Heywood. On Diversity, Teaming, and Hierarchical Policies: Observations from the Keepaway Soccer Task. In proceedings of the 17th European Conference on Genetic Programming, 2014 pdf
Stephen Kelly, Peter Lichodzijewski, and Malcolm I. Heywood. On run time libraries and hierarchical symbiosis. In Proceedings of the 2012 IEEE Congress on Evolutionary Computation, pages 1-8, 2012 pdf
Stephen Kelly, Peter. Lichodzijewski, and Malcolm I. Heywood. On Symbiotic Policy Search and Multi-Level Selection. In Proceedings of Artificial Life 13, the Thirteenth International Conference on the Simulation and Synthesis of Living Systems, pages 559-560, 2012
Theses
Stephen Kelly. Scaling Genetic Programming to Challenging Reinforcement Tasks through Emergent Modularity. PhD Thesis, Dalhousie University, 2018 pdf
Stephen Kelly. On Developmental Variation in Hierarchical Symbiotic Policy Search. Master's Thesis, Dalhousie University, 2012