CDRL：一种受小脑回路和树突计算策略启发的强化学习框架
CDRL: A Reinforcement Learning Framework Inspired by Cerebellar Circuits and Dendritic Computational Strategies
AI总结：
CDRL通过借鉴小脑回路和树突计算策略，提出了一种提升强化学习样本效率、鲁棒性和泛化能力的生物启发架构。
摘要：
强化学习（RL）在高维序列决策任务中取得了显著成效，但仍受限于低样本效率、对噪声的敏感性以及在部分可观测性下的弱泛化能力。现有方法主要通过优化策略解决这些问题，而架构先验在塑造表征学习和决策动态中的作用尚待探索。受小脑结构原理启发，我们提出了一种生物基础的RL架构，该架构整合了大规模扩展、稀疏连接、稀疏激活以及树突级调节。在噪声高维RL基准测试中，实验表明，小脑架构和树突调节在样本效率、鲁棒性和泛化能力方面均优于传统设计。对架构参数的敏感性分析表明，小脑启发的结构可为参数受限的RL提供优化性能。总体而言，我们的工作强调了小脑结构先验作为RL有效归纳偏置的价值。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
