Phylogeny-Informed Interaction Estimation Accelerates Co-Evolutionary Learning

• URL: http://arxiv.org/abs/2404.06588v1
• Date: Tue, 9 Apr 2024 19:29:19 GMT
• Title: Phylogeny-Informed Interaction Estimation Accelerates Co-Evolutionary Learning
• Authors: Jack Garbus, Thomas Willkens, Alexander Lalejini, Jordan Pollack,
• Abstract summary: We introduce phylogeny-informed interaction estimation, which uses phylogenetic analysis to estimate interaction outcomes. We find that phylogeny-informed estimation can substantially reduce the computation required to solve problems.
• Score: 42.642008092347986
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Neural Amortized Inference for Nested Multi-agent Reasoning [54.39127942041582]
  We propose a novel approach to bridge the gap between human-like inference capabilities and computational limitations. We evaluate our method in two challenging multi-agent interaction domains.
  arXiv  Detail & Related papers  (2023-08-21T22:40:36Z)
• Phylogeny-informed fitness estimation [58.720142291102135]
  We propose phylogeny-informed fitness estimation, which exploits a population's phylogeny to estimate fitness evaluations. Our results indicate that phylogeny-informed fitness estimation can mitigate the drawbacks of down-sampled lexicase. This work serves as an initial step toward improving evolutionary algorithms by exploiting runtime phylogenetic analysis.
  arXiv  Detail & Related papers  (2023-06-06T19:05:01Z)
• Biophysical Cybernetics of Directed Evolution and Eco-evolutionary Dynamics [0.0]
  We introduce a duality which maps the complexity of accounting for both ecology and individual genotypic/phenotypic types. We attack the problem of "directed evolution" in the form of a Partially Observable Markov Decision Process. This provides a tractable case of studying eco-evolutionary trajectories of a highly general type.
  arXiv  Detail & Related papers  (2023-05-05T07:45:28Z)
• When to be critical? Performance and evolvability in different regimes of neural Ising agents [18.536813548129878]
  It has long been hypothesized that operating close to the critical state is beneficial for natural, artificial and their evolutionary systems. We put this hypothesis to test in a system of evolving foraging agents controlled by neural networks. Surprisingly, we find that all populations that discover solutions, evolve to be subcritical.
  arXiv  Detail & Related papers  (2023-03-28T17:57:57Z)
• Predicting the long-term collective behaviour of fish pairs with deep learning [52.83927369492564]
  This study introduces a deep learning model to assess social interactions in the fish species Hemigrammus rhodostomus. We compare the results of our deep learning approach to experiments and to the results of a state-of-the-art analytical model. We demonstrate that machine learning models social interactions can directly compete with their analytical counterparts in subtle experimental observables.
  arXiv  Detail & Related papers  (2023-02-14T05:25:03Z)
• Learning Swarm Interaction Dynamics from Density Evolution [0.0]
  We consider the problem of understanding the coordinated movements of biological or artificial swarms. We describe the dynamics of the swarm based on pairwise interactions according to a Cucker-Smale flocking model. We incorporate the augmented system in an iterative optimization scheme to learn the dynamics of the interacting agents from observations of the swarm's density evolution.
  arXiv  Detail & Related papers  (2021-12-05T20:18:48Z)
• Overcoming the Domain Gap in Contrastive Learning of Neural Action Representations [60.47807856873544]
  A fundamental goal in neuroscience is to understand the relationship between neural activity and behavior. We generated a new multimodal dataset consisting of the spontaneous behaviors generated by fruit flies. This dataset and our new set of augmentations promise to accelerate the application of self-supervised learning methods in neuroscience.
  arXiv  Detail & Related papers  (2021-11-29T15:27:51Z)
• A Comparative Study of Machine Learning Methods for Predicting the Evolution of Brain Connectivity from a Baseline Timepoint [0.0]
  Predicting the evolution of the brain network, also called connectome, makes it possible to spot connectivity-related neurological disorders in earlier stages. We organized a Kaggle competition where 20 competing teams designed advanced machine learning pipelines for predicting the brain connectivity evolution from a single timepoint.
  arXiv  Detail & Related papers  (2021-09-16T06:13:49Z)
• Harnessing Heterogeneity: Learning from Decomposed Feedback in Bayesian Modeling [68.69431580852535]
  We introduce a novel GP regression to incorporate the subgroup feedback. Our modified regression has provably lower variance -- and thus a more accurate posterior -- compared to previous approaches. We execute our algorithm on two disparate social problems.
  arXiv  Detail & Related papers  (2021-07-07T03:57:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.