CDRL: A Reinforcement Learning Framework Inspired by Cerebellar Circuits and Dendritic Computational Strategies

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Sibo, Jing, Rui, Lv, Liangfu, Zhang, Jian, Zang, Yunliang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915801627361280
author Zhang, Sibo
Jing, Rui
Lv, Liangfu
Zhang, Jian
Zang, Yunliang
author_facet Zhang, Sibo
Jing, Rui
Lv, Liangfu
Zhang, Jian
Zang, Yunliang
contents Reinforcement learning (RL) has achieved notable performance in high-dimensional sequential decision-making tasks, yet remains limited by low sample efficiency, sensitivity to noise, and weak generalization under partial observability. Most existing approaches address these issues primarily through optimization strategies, while the role of architectural priors in shaping representation learning and decision dynamics is less explored. Inspired by structural principles of the cerebellum, we propose a biologically grounded RL architecture that incorporate large expansion, sparse connectivity, sparse activation, and dendritic-level modulation. Experiments on noisy, high-dimensional RL benchmarks show that both the cerebellar architecture and dendritic modulation consistently improve sample efficiency, robustness, and generalization compared to conventional designs. Sensitivity analysis of architectural parameters suggests that cerebellum-inspired structures can offer optimized performance for RL with constrained model parameters. Overall, our work underscores the value of cerebellar structural priors as effective inductive biases for RL.
format Preprint
id arxiv_https___arxiv_org_abs_2602_15367
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CDRL: A Reinforcement Learning Framework Inspired by Cerebellar Circuits and Dendritic Computational Strategies
Zhang, Sibo
Jing, Rui
Lv, Liangfu
Zhang, Jian
Zang, Yunliang
Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
Reinforcement learning (RL) has achieved notable performance in high-dimensional sequential decision-making tasks, yet remains limited by low sample efficiency, sensitivity to noise, and weak generalization under partial observability. Most existing approaches address these issues primarily through optimization strategies, while the role of architectural priors in shaping representation learning and decision dynamics is less explored. Inspired by structural principles of the cerebellum, we propose a biologically grounded RL architecture that incorporate large expansion, sparse connectivity, sparse activation, and dendritic-level modulation. Experiments on noisy, high-dimensional RL benchmarks show that both the cerebellar architecture and dendritic modulation consistently improve sample efficiency, robustness, and generalization compared to conventional designs. Sensitivity analysis of architectural parameters suggests that cerebellum-inspired structures can offer optimized performance for RL with constrained model parameters. Overall, our work underscores the value of cerebellar structural priors as effective inductive biases for RL.
title CDRL: A Reinforcement Learning Framework Inspired by Cerebellar Circuits and Dendritic Computational Strategies
topic Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
url https://arxiv.org/abs/2602.15367