NDLI: Evolutionary feature evaluation for online Reinforcement Learning

Content Provider	IEEE Xplore Digital Library
Author	Bishop, J. Miikkulainen, R.
Copyright Year	2013
Description	Author affiliation: Dept. of Comput. Sci., Univ. of Texas at Austin, Austin, TX, USA (Bishop, J.; Miikkulainen, R.)
Abstract	Most successful examples of Reinforcement Learning (RL) report the use of carefully designed features, that is, a representation of the problem state that facilitates effective learning. The best features cannot always be known in advance, creating the need to evaluate more features than will ultimately be chosen. This paper presents Temporal Difference Feature Evaluation (TDFE), a novel approach to the problem of feature evaluation in an online RL agent. TDFE combines value function learning by temporal difference methods with an evolutionary algorithm that searches the space of feature subsets, and outputs franking over all individual features. TDFE dynamically adjusts its ranking, avoids the sample complexity multiplier of many population-based approaches, and works with arbitrary feature representations. Online learning experiments are performed in the game of Connect Four, establishing (i) that the choice of features is critical, (ii) that TDFE can evaluate and rank all the available features online, and (iii) that the ranking can be used effectively as the basis of dynamic online feature selection.
Starting Page	1
Ending Page	8
File Size	540139
Page Count	8
File Format	PDF
ISSN	23254289
e-ISBN	9781467353113
DOI	10.1109/CIG.2013.6633648
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2013-08-11
Publisher Place	Canada
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Frequency locked loops feature selectien Radiation detectors Sociology Matching pursuit algorithms Games Connect Four Reinforcement Learning Evolutionary Algorithms Statistics Standards online learning
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Evolutionary feature evaluation for online reinforcement learning.

Evolutionary Feature Evaluation for Online Reinforcement Learning

Effect of communication topologies on hybrid evolutionary algorithms

Evolutionary Feature Evaluation for Online Reinforcement Learning

Generalized motion compensation and arithmetic coding for matching pursuit coder

Evolutionary Feature Evaluation for Online Reinforcement Learning Julian

A fast-locking all-digital phase locked loop in 90nm CMOS for Gigascale systems

A two stage learning technique using PSO-based FLC and QFIS for the pursuit evasion differential game

The application of matching pursuit to extract vibration signalfeature

Evolutionary feature evaluation for online Reinforcement Learning

Similar Documents

Evolutionary feature evaluation for online reinforcement learning.

Evolutionary Feature Evaluation for Online Reinforcement Learning

Effect of communication topologies on hybrid evolutionary algorithms

Evolutionary Feature Evaluation for Online Reinforcement Learning

Generalized motion compensation and arithmetic coding for matching pursuit coder

Evolutionary Feature Evaluation for Online Reinforcement Learning Julian

A fast-locking all-digital phase locked loop in 90nm CMOS for Gigascale systems

A two stage learning technique using PSO-based FLC and QFIS for the pursuit evasion differential game

The application of matching pursuit to extract vibration signalfeature

Evolutionary feature evaluation for online Reinforcement Learning