Adaptive Path-Integral Approach to Representation Learning and Planning for Dynamical Systems

07/05/2018
by   Jung-Su Ha, et al.
0

We present a representation learning algorithm that learns a low-dimensional latent dynamical system from high-dimensional sequential raw data, e.g., video. The framework builds upon recent advances in amortized inference methods that use both an inference network and a refinement procedure to output samples from a variational distribution given an observation sequence, and takes advantage of the duality between control and inference to approximately solve the intractable inference problem using the path integral control approach. The learned dynamical model can be used to predict and plan the future states; we also present the efficient planning method that exploits the learned low-dimensional latent dynamics. Numerical experiments show that the proposed path-integral control based variational inference method leads to tighter lower bounds in statistical model learning of sequential data. The supplementary video can be found at https://youtu.be/4jDcbuAJ7mA.

READ FULL TEXT

page 8

page 9

research
07/05/2018

Adaptive Path-Integral Autoencoder: Representation Learning and Planning for Dynamical Systems

We present a representation learning algorithm that learns a low-dimensi...
research
07/24/2018

Learning Plannable Representations with Causal InfoGAN

In recent years, deep generative models have been shown to 'imagine' con...
research
08/27/2022

Deep Kernel Learning of Dynamical Models from High-Dimensional Noisy Data

This work proposes a Stochastic Variational Deep Kernel Learning method ...
research
09/02/2022

Introducing dynamical constraints into representation learning

While representation learning has been central to the rise of machine le...
research
11/22/2017

High-dimensional Motion Planning using Latent Variable Models via Approximate Inference

In this work, we present an efficient framework to generate a motion tra...
research
05/07/2020

Plan2Vec: Unsupervised Representation Learning by Latent Plans

In this paper we introduce plan2vec, an unsupervised representation lear...
research
10/02/2017

SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control

In this work, we present an approach to deep visuomotor control using st...

Please sign up or login with your details

Forgot password? Click here to reset