Physics-inspired neural networks (NNs), such as Hamiltonian or Lagrangian NNs, dramatically outperform other learned dynamics models by leveraging strong inductive biases. These models, however, are challenging to apply to many real world systems, such as those that don't conserve energy or contain contacts, a common setting for robotics and reinforcement learning. In this paper, we examine the inductive biases that make physics-inspired models successful in practice. We show that, contrary to conventional wisdom, the improved generalization of HNNs is the result of modeling acceleration directly and avoiding artificial complexity from the coordinate system, rather than symplectic structure or energy conservation. We show that by relaxing the inductive biases of these models, we can match or exceed performance on energy-conserving systems while dramatically improving performance on practical, non-conservative systems. We extend this approach to constructing transition models for common Mujoco environments, showing that our model can appropriately balance inductive biases with the flexibility required for model-based control.
翻译:物理学启发神经网络(NNs),如汉密尔顿或拉格朗日神经网络(Lagrangian NNs),通过利用强烈的感应偏差,大大优于其他学习的动态模型。然而,这些模型具有挑战性,难以适用于许多真实的世界系统,例如那些不节能或含有接触的系统、机器人的共同环境以及强化学习。在本文中,我们研究了使物理学启发模型在实践中取得成功的诱导偏差。我们发现,与传统智慧相反,改进HNS的普及化是直接模拟加速和避免协调系统人为复杂性的结果,而不是模拟结构或节能的结果。我们通过放松这些模型的诱导偏差,可以匹配或超过节能系统的性能,同时大大改善实用、非节能系统的性能。我们推广了这一方法,为普通的Mujoco环境构建过渡模型,表明我们的模型能够适当地平衡感想偏向与基于模型的控制所需的灵活性。