Network bottlenecks and task structure control the evolution of interpretable learning rules in a foraging agent

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Giannakakis, Emmanouil, Khajehabdollahi, Sina, Levina, Anna
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929283030581248
author Giannakakis, Emmanouil
Khajehabdollahi, Sina
Levina, Anna
author_facet Giannakakis, Emmanouil
Khajehabdollahi, Sina
Levina, Anna
contents 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 to 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_13649
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Network bottlenecks and task structure control the evolution of interpretable learning rules in a foraging agent
Giannakakis, Emmanouil
Khajehabdollahi, Sina
Levina, Anna
Neurons and Cognition
Neural and Evolutionary Computing
Adaptation and Self-Organizing Systems
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 to 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.
title Network bottlenecks and task structure control the evolution of interpretable learning rules in a foraging agent
topic Neurons and Cognition
Neural and Evolutionary Computing
Adaptation and Self-Organizing Systems
url https://arxiv.org/abs/2403.13649