Systematic Generalization for Predictive Control in Multivariate Time Series

by   Hritik Bansal, et al.

Prior work has focused on evaluating the ability of neural networks to reason about novel combinations from known components, an intrinsic property of human cognition. In this work, we aim to study systematic generalization in predicting future state trajectories of a dynamical system, conditioned on past states' trajectory (dependent variables), past and future actions (control variables). In our context, systematic generalization implies that a good model should perform well on all new combinations of future actions after being trained on all of them, but only on a limited set of their combinations. For models to generalize out-of-distribution to unseen action combinations, they should reason about the states and their dependency relation with the applied actions. We conduct a rigorous study of useful inductive biases that learn to predict the trajectories up to large horizons well, and capture true dependency relations between the states and the controls through our synthetic setup, and simulated data from electric motors.


Prediction and Control with Temporal Segment Models

We introduce a method for learning the dynamics of complex nonlinear sys...

MoCoDA: Model-based Counterfactual Data Augmentation

The number of states in a dynamic process is exponential in the number o...

ORCHARD: A Benchmark For Measuring Systematic Generalization of Multi-Hierarchical Reasoning

The ability to reason with multiple hierarchical structures is an attrac...

Generalizable Features From Unsupervised Learning

Humans learn a predictive model of the world and use this model to reaso...

Learning Predictive Models for Ergonomic Control of Prosthetic Devices

We present Model-Predictive Interaction Primitives – a robot learning fr...

On the Capability of Neural Networks to Generalize to Unseen Category-Pose Combinations

Recognizing an object's category and pose lies at the heart of visual un...

Code Repositories



view repo

Please sign up or login with your details

Forgot password? Click here to reset