Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Phylogeny-Informed Interaction Estimation Accelerates Co-Evolutionary Learning (2404.06588v1)

Published 9 Apr 2024 in cs.NE

Abstract: Co-evolution is a powerful problem-solving approach. However, fitness evaluation in co-evolutionary algorithms can be computationally expensive, as the quality of an individual in one population is defined by its interactions with many (or all) members of one or more other populations. To accelerate co-evolutionary systems, we introduce phylogeny-informed interaction estimation, which uses runtime phylogenetic analysis to estimate interaction outcomes between individuals based on how their relatives performed against each other. We test our interaction estimation method with three distinct co-evolutionary systems: two systems focused on measuring problem-solving success and one focused on measuring evolutionary open-endedness. We find that phylogeny-informed estimation can substantially reduce the computation required to solve problems, particularly at the beginning of long-term evolutionary runs. Additionally, we find that our estimation method initially jump-starts the evolution of neural complexity in our open-ended domain, but estimation-free systems eventually "catch-up" if given enough time. More broadly, continued refinements to these phylogeny-informed interaction estimation methods offers a promising path to reducing the computational cost of running co-evolutionary systems while maintaining their open-endedness.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. An evolutionary algorithm that constructs recurrent neural networks. IEEE Transactions on Neural Networks, 5(1):54–65.
  2. Evolutionary Module Acquisition. The Second Annual Conference on Evolutionary Programming, page 11.
  3. Arrojo, M. P. (2018). Investigating Coevolutionary Algorithms For Expensive Fitness Evaluations In Cybersecurity.
  4. Informed Down-Sampled Lexicase Selection: Identifying productive training cases for efficient problem solving. arXiv:2301.01488 [cs].
  5. Fitness inheritance for noisy evolutionary multi-objective optimization. In Proceedings of the 7th annual conference on Genetic and evolutionary computation, pages 779–785, Washington DC USA. ACM.
  6. Quantifying the Tape of Life: Ancestry-based Metrics Provide Insights and Intuition about Evolutionary Dynamics. In The 2018 Conference on Artificial Life, pages 75–82, Tokyo, Japan. MIT Press.
  7. Adaptive Fitness Predictors in Coevolutionary Cartesian Genetic Programming. Evolutionary Computation, 27(3):497–523.
  8. Competitive coevolution for defense and security: Elo-based similar-strength opponent sampling. In Proceedings of the Genetic and Evolutionary Computation Conference Companion, pages 1898–1906, Lille France. ACM.
  9. Random subsampling improves performance in lexicase selection. In Proceedings of the Genetic and Evolutionary Computation Conference Companion, pages 2028–2031, Prague Czech Republic. ACM.
  10. A suite of diagnostic metrics for characterizing selection schemes. arXiv:2204.13839 [cs].
  11. Hillis, W. (1990). Co-evolving parasites improve simulated evolution as an optimization procedure. Physica D: Nonlinear Phenomena, 42(1-3):228–234.
  12. Ideal Evaluation from Coevolution. Evolutionary Computation, 12(2):159–192.
  13. Data Standards for Artificial Life Software. pages 507–514, Newcastle, United Kingdom. MIT Press.
  14. Phylogeny-informed fitness estimation. arXiv:2306.03970 [cs].
  15. The Evolutionary Origins of Phenotypic Plasticity. In Proceedings of the Artificial Life Conference 2016, pages 372–379, Cancun, Mexico. MIT Press.
  16. The evolutionary origin of complex features. Nature, 423(6936):139–144.
  17. Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey. arXiv:2401.11963 [cs].
  18. Surrogate Fitness via Factorization of Interaction Matrix. In Genetic Programming, volume 9594, pages 68–82. Springer International Publishing, Cham. Series Title: Lecture Notes in Computer Science.
  19. Online Discovery of Search Objectives for Test-based Problems.
  20. Neural estimation of interaction outcomes. In Proceedings of the Genetic and Evolutionary Computation Conference, pages 1055–1062, Kyoto Japan. ACM.
  21. Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning.
  22. Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination. In Proceedings of the 37th International Conference on Machine Learning, pages 6651–6660. PMLR. ISSN: 2640-3498.
  23. Designing Electronic Circuits Using Evolutionary Algorithms. Arithmetic Circuits: A Case Study. Genetic Algorithms and Evolution Strategies in Engineering and Computer Science.
  24. Toward Phylogenetic Inference of Evolutionary Dynamics at Scale. In The 2023 Conference on Artificial Life. MIT Press.
  25. Speeding-Up Expensive Evaluations in High-Level Synthesis Using Solution Modeling and Fitness Inheritance. In Hiot, L. M., Ong, Y. S., Tenne, Y., and Goh, C.-K., editors, Computational Intelligence in Expensive Optimization Problems, volume 2, pages 701–723. Springer Berlin Heidelberg, Berlin, Heidelberg. Series Title: Evolutionary Learning and Optimization.
  26. Fitness inheritance in evolutionary and multi-objective high-level synthesis. In 2007 IEEE Congress on Evolutionary Computation, pages 3459–3466, Singapore. IEEE.
  27. Coevolution of Fitness Predictors. IEEE Transactions on Evolutionary Computation, 12(6):736–749.
  28. Spector, L. (2012). Assessment of problem modality by differential performance of lexicase selection in genetic programming: a preliminary report. GECCO ’12: Proceedings of the 14th annual conference companion on Genetic and evolutionary computation.
  29. Stanley, K. O. (2007). Compositional pattern producing networks: A novel abstraction of development. Genetic Programming and Evolvable Machines, 8(2):131–162.
  30. A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks. Artificial Life, 15(2):185–212.
  31. Open-Ended Evolution: Perspectives from the OEE Workshop in York. Artificial Life, 22(3):408–423.
  32. Coevolutionary Dynamics in a Minimal Substrate. In Proceedings of the 3rd Annual Conference on Genetic and Evolutionary Computation, GECCO’01, pages 702–709, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc. event-place: San Francisco, California.
  33. Evolving Unbounded Neural Complexity in Pursuit-Evasion Games. Online. MIT Press.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets