Beta DVBF: Learning State-Space Models for Control from High Dimensional Observations

11/02/2019
by   Neha Das, et al.
8

Learning a model of dynamics from high-dimensional images can be a core ingredient for success in many applications across different domains, especially in sequential decision making. However, currently prevailing methods based on latent-variable models are limited to working with low resolution images only. In this work, we show that some of the issues with using high-dimensional observations arise from the discrepancy between the dimensionality of the latent and observable space, and propose solutions to overcome them.

READ FULL TEXT

page 6

page 7

page 8

page 12

page 14

research
03/02/2020

Predictive Coding for Locally-Linear Control

High-dimensional observations and unknown dynamics are major challenges ...
research
09/04/2019

Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control

Many real-world sequential decision-making problems can be formulated as...
research
06/06/2019

DeepMDP: Learning Continuous Latent Space Models for Representation Learning

Many reinforcement learning (RL) tasks provide the agent with high-dimen...
research
03/26/2020

Gaussian-Dirichlet Random Fields for Inference over High Dimensional Categorical Observations

We propose a generative model for the spatio-temporal distribution of hi...
research
06/23/2023

Prediction under Latent Subgroup Shifts with High-Dimensional Observations

We introduce a new approach to prediction in graphical models with laten...
research
08/02/2022

A Recursive Partitioning Approach for Dynamic Discrete Choice Modeling in High Dimensional Settings

Dynamic discrete choice models are widely employed to answer substantive...
research
10/07/2019

Increasing Expressivity of a Hyperspherical VAE

Learning suitable latent representations for observed, high-dimensional ...

Please sign up or login with your details

Forgot password? Click here to reset