A Bio-Inspired Minimal Model for Non-Stationary K-Armed Bandits

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Danieli, Krubeal, Lepperød, Mikkel Elle
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916971841323008
author Danieli, Krubeal
Lepperød, Mikkel Elle
author_facet Danieli, Krubeal
Lepperød, Mikkel Elle
contents While reinforcement learning algorithms have made significant progress in solving multi-armed bandit problems, they often lack biological plausibility in architecture and dynamics. Here, we propose a bio-inspired neural model based on interacting populations of rate neurons, drawing inspiration from the orbitofrontal cortex and anterior cingulate cortex. Our model reports robust performance across various stochastic bandit problems, matching the effectiveness of standard algorithms such as Thompson Sampling and UCB. Notably, the model exhibits adaptive behavior: employing greedy strategies in low-uncertainty situations while increasing exploratory behavior as uncertainty rises. Through evolutionary optimization, the model's hyperparameters converged to values that align with known synaptic mechanisms, particularly in terms of synapse-dependent neural activity and learning rate adaptation. These findings suggest that biologically-inspired computational architectures can achieve competitive performance while providing insights into neural mechanisms of decision-making under uncertainty.
format Preprint
id arxiv_https___arxiv_org_abs_2509_22209
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Bio-Inspired Minimal Model for Non-Stationary K-Armed Bandits
Danieli, Krubeal
Lepperød, Mikkel Elle
Neurons and Cognition
While reinforcement learning algorithms have made significant progress in solving multi-armed bandit problems, they often lack biological plausibility in architecture and dynamics. Here, we propose a bio-inspired neural model based on interacting populations of rate neurons, drawing inspiration from the orbitofrontal cortex and anterior cingulate cortex. Our model reports robust performance across various stochastic bandit problems, matching the effectiveness of standard algorithms such as Thompson Sampling and UCB. Notably, the model exhibits adaptive behavior: employing greedy strategies in low-uncertainty situations while increasing exploratory behavior as uncertainty rises. Through evolutionary optimization, the model's hyperparameters converged to values that align with known synaptic mechanisms, particularly in terms of synapse-dependent neural activity and learning rate adaptation. These findings suggest that biologically-inspired computational architectures can achieve competitive performance while providing insights into neural mechanisms of decision-making under uncertainty.
title A Bio-Inspired Minimal Model for Non-Stationary K-Armed Bandits
topic Neurons and Cognition
url https://arxiv.org/abs/2509.22209