Network Bottlenecks and Task Structure Control the Evolution of Interpretable Learning Rules in a Foraging Agent.

Autor:	Giannakakis E; University of Tübingen, Department of Computer Science, Max Planck Institute for Biological Cybernetics. giannakakismanos@gmail.com., Khajehabdollahi S; University of Tübingen, Department of Computer Science., Levina A; University of Tübingen, Department of Computer Science, Max Planck Institute for Biological Cybernetics, Bernstein Center for Computational Neuroscience Tübingen.
Jazyk:	angličtina
Zdroj:	Artificial life [Artif Life] 2024 Oct 31, pp. 1-18. Date of Electronic Publication: 2024 Oct 31.
DOI:	10.1162/artl_a_00458
Abstrakt:	Developing reliable mechanisms for continuous local learning is a central challenge faced by biological and artificial systems. Yet, how the environmental factors and structural constraints on the learning network influence the optimal plasticity mechanisms remains obscure even for simple settings. To elucidate these dependencies, we study meta-learning via evolutionary optimization of simple reward-modulated plasticity rules in embodied agents solving a foraging task. We show that unconstrained meta-learning leads to the emergence of diverse plasticity rules. However, regularization and bottlenecks in the model help reduce this variability, resulting in interpretable rules. Our findings indicate that the meta-learning of plasticity rules is very sensitive to various parameters, with this sensitivity possibly reflected in the learning rules found in biological networks. When included in models, these dependencies can be used to discover potential objective functions and details of biological learning via comparisons with experimental observations. (© 2024 Massachusetts Institute of Technology.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu