论文标题
Dynode：连续控制中动态建模的神经常见微分方程
DyNODE: Neural Ordinary Differential Equations for Dynamics Modeling in Continuous Control
论文作者
论文摘要
我们提出了一种新颖的方法（Dynode），该方法通过将控制纳入神经常规微分方程框架中来捕获系统的基本动力学。我们对动态建模的方法和标准神经网络体系结构进行了系统的评估和比较。我们的结果表明，与Actor-Critic批判性增强学习（RL）算法结合使用时，使用模型预测来改善评论家的目标值，均超过了经典的神经网络，无论是在样本效率和预测性能方面都超过了经常使用的连续任务范围，这些范围经常使用，这些任务经常用于排序RL ALGORITHS。这种方法为开发模型提供了新的途径，这些模型更适合学习动态系统的演变，在基于模型的强化学习的背景下尤其有用。为了帮助相关工作，我们已在https://github.com/vmartinezalvarez/dynode上提供代码。
We present a novel approach (DyNODE) that captures the underlying dynamics of a system by incorporating control in a neural ordinary differential equation framework. We conduct a systematic evaluation and comparison of our method and standard neural network architectures for dynamics modeling. Our results indicate that a simple DyNODE architecture when combined with an actor-critic reinforcement learning (RL) algorithm that uses model predictions to improve the critic's target values, outperforms canonical neural networks, both in sample efficiency and predictive performance across a diverse range of continuous tasks that are frequently used to benchmark RL algorithms. This approach provides a new avenue for the development of models that are more suited to learn the evolution of dynamical systems, particularly useful in the context of model-based reinforcement learning. To assist related work, we have made code available at https://github.com/vmartinezalvarez/DyNODE .
