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

2026-02-17 · Sibo Zhang, Rui Jing, Liangfu Lv, Jian Zhang, Yunliang Zang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.15367

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning Reinforcement Learning

An Analysis of Categorical Distributional Reinforcement Learning

2018-02-22 · Mark Rowland, Marc G. Bellemare, Will Dabney, Rémi Munos 외

Distributional approaches to value-based reinforcement learning model the entire distribution of returns, rather than just their expected values, and have recently been shown to yield state-of-the-art empirical performan…

Distributional Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

CDRL: Certification-Driven Reinforcement Learning for Neutrino Flavor Model Discovery

2026-08-21 · Piyush Jha, Jake Rudolph, Victoria Knapp-Pérez, Max Fieg 외 arxiv

Many scientific discovery problems require searching combinatorial hypothesis spaces under complex domain constraints. Reinforcement learning (RL) offers a promising approach, but existing methods rely on scalar rewards …

Reinforcement Learning

A optimization framework for herbal prescription planning based on deep reinforcement learning

2023-04-25 · Kuo Yang, Zecong Yu, Xin Su, Xiong He 외

Treatment planning for chronic diseases is a critical task in medical artificial intelligence, particularly in traditional Chinese medicine (TCM). However, generating optimized sequential treatment strategies for patient…

Deep Reinforcement Learning reinforcement-learning Sequential Diagnosis

Cerebellar-Inspired Residual Control for Fault Recovery: From Inference-Time Adaptation to Structural Consolidation

2026-02-06 · Nethmi Jayasinghe, Diana Gontero, Spencer T. Brown, Vinod K. Sangwan 외 arxiv

Robotic policies deployed in real-world environments often encounter post-training faults, where retraining, exploration, or system identification are impractical. We introduce an inference-time, cerebellar-inspired resi…

Reinforcement Learning

Collaborative Deep Reinforcement Learning

2017-02-19 · Kaixiang Lin, Shu Wang, Jiayu Zhou

Besides independent learning, human learning process is highly improved by summarizing what has been learned, communicating it with peers, and subsequently fusing knowledge from different sources to assist the current le…

Deep Reinforcement Learning Knowledge Distillation OpenAI Gym reinforcement-learning+3