NDLI: A stochastic approximation method with max-norm projections and its applications to the Q-learning algorithm

Content Provider	ACM Digital Library
Author	Kunnumkal, Sumit Topaloglu, Huseyin
Copyright Year	2010
Abstract	In this article, we develop a stochastic approximation method to solve a monotone estimation problem and use this method to enhance the empirical performance of the Q-learning algorithm when applied to Markov decision problems with monotone value functions. We begin by considering a monotone estimation problem where we want to estimate the expectation of a random vector, η. We assume that the components of E {η} are known to be in increasing order. The stochastic approximation method that we propose is designed to exploit this information by projecting its iterates onto the set of vectors with increasing components. The novel aspect of the method is that it uses projections with respect to the max norm. We show the almost sure convergence of the stochastic approximation method. After this result, we consider the Q-learning algorithm when applied to Markov decision problems with monotone value functions. We study a variant of the Q-learning algorithm that uses projections to ensure that the value function approximation obtained at each iteration is also monotone. Computational results indicate that the performance of the Q-learning algorithm can be improved significantly by exploiting the monotonicity property of the value functions.
Starting Page	1
Ending Page	26
Page Count	26
File Format	PDF
ISSN	10493301
e-ISSN	15581195
DOI	10.1145/1842713.1842715
Volume Number	20
Issue Number	3
Journal	ACM Transactions on Modeling and Computer Simulation (TOMACS)
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2010-10-07
Publisher Place	New York
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	Q-learning Stochastic approximation Max-norm projection
Content Type	Text
Resource Type	Article
Subject	Computer Science Applications Modeling and Simulation

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

A stochastic approximation method with max-norm projections and its applications to the q-learning algorithm (2009).

Stochastic Approximation Approaches to the Stochastic Variational Inequality Problem

The stochastic root-finding problem: Overview, solutions, and open questions

Fast projections onto mixed-norm balls with applications

Parallel simulation of stochastic Petri nets using recurrence equations

Retrospective-approximation algorithms for the multidimensional stochastic root-finding problem

Smoothed Functional Algorithms for Stochastic Optimization Using $\textit{q}-Gaussian$ Distributions

Model-Based Annealing Random Search with Stochastic Averaging

Multidimensional stochastic approximation: Adaptive algorithms and applications

A stochastic approximation method with max-norm projections and its applications to the Q-learning algorithm

Similar Documents

A stochastic approximation method with max-norm projections and its applications to the q-learning algorithm (2009).

Stochastic Approximation Approaches to the Stochastic Variational Inequality Problem

The stochastic root-finding problem: Overview, solutions, and open questions

Fast projections onto mixed-norm balls with applications

Parallel simulation of stochastic Petri nets using recurrence equations

Retrospective-approximation algorithms for the multidimensional stochastic root-finding problem

Smoothed Functional Algorithms for Stochastic Optimization Using $\textit{q}-Gaussian$ Distributions

Model-Based Annealing Random Search with Stochastic Averaging

Multidimensional stochastic approximation: Adaptive algorithms and applications

A stochastic approximation method with max-norm projections and its applications to the Q-learning algorithm