English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Curiosity-driven learning with Context Tree Weighting

Peng, Z., & Braun, D. (2014). Curiosity-driven learning with Context Tree Weighting. In 4th Joint International Conference on Development and Learning and on Epigenetic Robotics (IEEE ICDL-Epirob 2014) (pp. 366-367). Piscataway, NJ, USA: IEEE.

Item is

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Peng, Zhen1, 2, Author              
Braun, DA1, 2, Author              
Affiliations:
1Research Group Sensorimotor Learning and Decision-Making, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497809              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: In the first simulation, the intrinsic motivation of the agent was given by measuring learning progress through reduction in informational surprise (Figure 1 A-C). This way the agent should first learn the action that is easiest to learn (a1), and then switch to other actions that still allow for learning (a2) and ignore actions that cannot be learned at all (a3). This is exactly what we found in our simple environment. Compared to the original developmental learning algorithm based on learning progress proposed by Oudeyer [2], our Context Tree Weighting approach does not require local experts to do prediction, rather it learns the conditional probability distribution over observations given action in one structure. In the second simulation, the intrinsic motivation of the agent was given by measuring compression progress through improvement in compressibility (Figure 1 D-F). The agent behaves similarly: the agent first concentrates on the action with the most predictable consequence and then switches over to the regular action where the consequence is more difficult to predict, but still learnable. Unlike the previous simulation, random actions are also interesting to some extent because the compressed symbol strings use 8-bit representations, while only 2 bits are required for our observation space. Our preliminary results suggest that Context Tree Weighting might provide a useful representation to study problems of development.

Details

show
hide
Language(s):
 Dates: 2014-10
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1109/DEVLRN.2014.6983008
BibTex Citekey: PengB2014
 Degree: -

Event

show
hide
Title: 4th Joint International Conference on Development and Learning and on Epigenetic Robotics (IEEE ICDL-Epirob 2014)
Place of Event: Genova, Italy
Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show
hide
Title: 4th Joint International Conference on Development and Learning and on Epigenetic Robotics (IEEE ICDL-Epirob 2014)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Piscataway, NJ, USA : IEEE
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 366 - 367 Identifier: ISBN: 978-1-4799-7540-2