KAN-Dreamer：基于Kolmogorov-Arnold网络作为函数近似器的世界模型基准测试
KAN-Dreamer: Benchmarking Kolmogorov-Arnold Networks as Function Approximators in World Models
AI总结：
KAN-Dreamer将Kolmogorov-Arnold网络整合到DreamerV3中，通过替代MLP和卷积组件，实现了样本效率和训练速度与原始架构相当的性能。
摘要：
DreamerV3是一种最先进的在线模型驱动强化学习（MBRL）算法，以显著的样本效率著称。同时，Kolmogorov-Arnold网络（KANs）作为一种多层感知机（MLP）的替代方案，提供了更优越的参数效率和可解释性。为缓解KANs的计算开销，变种如FastKAN利用径向基函数（RBFs）来加速推理。在本工作中，我们研究将KAN架构整合到DreamerV3框架中。我们引入KAN-Dreamer，用KAN和FastKAN层替换DreamerV3中的特定MLP和卷积组件。为确保在基于JAX的世界模型中的效率，我们实现了一个定制的、完全向量化的版本，具有简化了的网格管理。我们将研究分为三个子系统：视觉感知、潜在预测和行为学习。在DeepMind控制套件（walker_walk）上的实证评估分析了样本效率、训练时间和渐近性能。实验结果表明，使用我们适配的FastKAN作为奖励和继续预测器的直接替换，其性能与原始MLP架构相当，在样本效率和训练速度上保持一致。本报告为未来KAN世界模型的发展提供了初步研究。
英文摘要：
DreamerV3 is a state-of-the-art online model-based reinforcement learning (MBRL) algorithm known for remarkable sample efficiency. Concurrently, Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to Multi-Layer Perceptrons (MLPs), offering superior parameter efficiency and interpretability. To mitigate KANs' computational overhead, variants like FastKAN leverage Radial Basis Functions (RBFs) to accelerate inference. In this work, we investigate integrating KAN architectures into the DreamerV3 framework. We introduce KAN-Dreamer, replacing specific MLP and convolutional components of DreamerV3 with KAN and FastKAN layers. To ensure efficiency within the JAX-based World Model, we implement a tailored, fully vectorized version with simplified grid management. We structure our investigation into three subsystems: Visual Perception, Latent Prediction, and Behavior Learning. Empirical evaluations on the DeepMind Control Suite (walker_walk) analyze sample efficiency, training time, and asymptotic performance. Experimental results demonstrate that utilizing our adapted FastKAN as a drop-in replacement for the Reward and Continue predictors yields performance on par with the original MLP-based architecture, maintaining parity in both sample efficiency and training speed. This report serves as a preliminary study for future developments in KAN-based world models.
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。
