paper-with-me

홈 › Papers

Disentangling the independently controllable factors of variation by interacting with the world

2018-02-26 · Valentin Thomas, Emmanuel Bengio, William Fedus, Jules Pondard, Philippe Beaudoin, Hugo Larochelle, Joelle Pineau, Doina Precup, Yoshua Bengio

It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most previous work focuses on the static setting (e.g., with images), we postulate that some of the causal factors could be discovered if the learner is allowed to interact with its environment. The agent can experiment with different actions and observe their effects. More specifically, we hypothesize that some of these factors correspond to aspects of the environment which are independently controllable, i.e., that there exists a policy and a learnable feature for each such aspect of the environment, such that this policy can yield changes in that feature with minimal changes to other features that explain the statistical variations in the observed data. We propose a specific objective function to find such factors, and verify experimentally that it can indeed disentangle independently controllable aspects of the environment without any extrinsic reward signal.

📄 PDF Abstract BibTeX arXiv:1802.09484

Code (0)

등록된 구현이 없습니다.

Tasks

Open-Ended Question Answering

Similar Papers 제목 키워드 기반

Disentangling Controllable and Uncontrollable Factors of Variation by Interacting with the World

2018-04-19 · Yoshihide Sawada

We introduce a method to disentangle controllable and uncontrollable factors of variation by interacting with the world. Disentanglement leads to good representations and is important when applying deep neural networks (…

Disentanglementreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Independently Controllable Factors

2017-08-03 · Valentin Thomas, Jules Pondard, Emmanuel Bengio, Marc Sarfati 외

It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve t…

Open-Ended Question Answering

Disentangling Factors of Variation via Generative Entangling

2012-10-19 · Guillaume Desjardins, Aaron Courville, Yoshua Bengio

Here we propose a novel model family with the objective of learning to disentangle the factors of variation in data. Our approach is based on the spike-and-slab restricted Boltzmann machine which we generalize to include…

General Classification

Reference-based Variational Autoencoders

2019-03-08 · ICLR Workshop LLD 2019 · Adrià Ruiz, Oriol Martinez, Xavier Binefa, Jakob Verbeek

Learning disentangled representations from visual data, where different high-level generative factors are independently encoded, is of importance for many computer vision tasks. Solving this problem, however, typically r…

AttributeConditional Image GenerationImage Generation

Independently Controllable Features

2017-03-22 · Emmanuel Bengio, Valentin Thomas, Joelle Pineau, Doina Precup 외

Finding features that disentangle the different causes of variation in real data is a difficult task, that has nonetheless received considerable attention in static domains like natural images. Interactive environments, …