LEADS: Learning Dynamical Systems that Generalize Across Environments

by   Yuan Yin, et al.

When modeling dynamical systems from real-world data samples, the distribution of data often changes according to the environment in which they are captured, and the dynamics of the system itself vary from one environment to another. Generalizing across environments thus challenges the conventional frameworks. The classical settings suggest either considering data as i.i.d. and learning a single model to cover all situations or learning environment-specific models. Both are sub-optimal: the former disregards the discrepancies between environments leading to biased solutions, while the latter does not exploit their potential commonalities and is prone to scarcity problems. We propose LEADS, a novel framework that leverages the commonalities and discrepancies among known environments to improve model generalization. This is achieved with a tailored training formulation aiming at capturing common dynamics within a shared model while additional terms capture environment-specific dynamics. We ground our approach in theory, exhibiting a decrease in sample complexity with our approach and corroborate these results empirically, instantiating it for linear dynamics. Moreover, we concretize this framework for neural networks and evaluate it experimentally on representative families of nonlinear dynamics. We show that this new setting can exploit knowledge extracted from environment-dependent data and improves generalization for both known and novel environments.


page 7

page 24

page 25

page 26

page 27


SpReME: Sparse Regression for Multi-Environment Dynamic Systems

Learning dynamical systems is a promising avenue for scientific discover...

Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Models

In this paper, we learn dynamics models for parametrized families of dyn...

Generalizing Graph ODE for Learning Complex System Dynamics across Environments

Learning multi-agent system dynamics has been extensively studied for va...

Generalizing to New Physical Systems via Context-Informed Dynamics Model

Data-driven approaches to modeling physical systems fail to generalize t...

A Generalist Dynamics Model for Control

We investigate the use of transformer sequence models as dynamics models...

Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems

We consider the setting of vector valued non-linear dynamical systems X_...

ED2: An Environment Dynamics Decomposition Framework for World Model Construction

Model-based reinforcement learning methods achieve significant sample ef...

Please sign up or login with your details

Forgot password? Click here to reset