English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Information theoretic approach to decision making in continuous domains

Solopchuk, O. (2021). Information theoretic approach to decision making in continuous domains. PhD Thesis, Université Catholique de Louvain, Ottignies-Louvain-la-Neuve, Belgium.

Item is

Files

show Files

Locators

show
hide
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Solopchuk, O1, Author           
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Information theory has been often used to analyse the interactions of agents with their environment. For example, frameworks of bounded rationality focus on tradeoffs between utility maximisation and information processing cost. Alternatively, frameworks of planning frequently focus on casting exploration as potential information gain. Here, we will apply multi-variable information decomposition in order to isolate interactions between the agent, its past and future sensations, and its future self. We will then discuss intuition behind the resulting terms and connections to several popular frameworks. Afterwards, we will focus on active sensing - a decision making framework that formalizes exploration as reduction of uncertainty about the current state of the environment. Despite strong theoretical justifications, active sensing has had limited applicability due to difficulty in estimating information gain. Here we will address this issue by proposing a linear approximation to information gain and by implementing efficient gradient-based action selection within an artificial neural network setting. We will compare information gain estimation with state of the art, and validate our model on an active sensing task based on MNIST dataset.

Details

show
hide
Language(s):
 Dates: 2021-03-17
 Publication Status: Issued
 Pages: -
 Publishing info: Ottignies-Louvain-la-Neuve, Belgium : Université Catholique de Louvain
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: PhD

Event

show

Legal Case

show

Project information

show

Source

show