Stochastic approximation for non-expansive maps : application to Q-learning algorithms

Stochastic approximation for non-expansive maps : application to Q-learning algorithms

Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1997.

Manylion Llyfryddiaeth
Prif Awdur:	Abounadi, Jinane, 1966-
Awduron Eraill:	Dimitri P. Bersekas.
Fformat:	Traethawd Ymchwil
Iaith:	eng
Cyhoeddwyd:	Massachusetts Institute of Technology 2005
Pynciau:	Electrical Engineering and Computer Science
Mynediad Ar-lein:	http://hdl.handle.net/1721.1/10033

Eitemau Tebyg

Asynchronous stochastic approximation and Q-learning
Cyhoeddwyd: (2003)

Approximation algorithms for stochastic scheduling problems
gan: Dean, Brian C. (Brian Christopher), 1975-
Cyhoeddwyd: (2006)

Approximation algorithms for stochastic scheduling on unrelated machines
gan: Scott, Jacob (Jacob Healy)
Cyhoeddwyd: (2009)

Realization and approximation of stationary stochastic processes
gan: Avniel, Yehuda
Cyhoeddwyd: (2005)

Q-learning and policy iteration algorithms for stochastic shortest path problems
gan: Yu, Huizhen, et al.
Cyhoeddwyd: (2015)

Stochastic realization theory for exact and approximate multiscale models
gan: Tucker, Dewey S. (Dewey Stanton)
Cyhoeddwyd: (2006)

Solving the reader collision problem with a hierarchical Q-learning algorithm
gan: Ho, Junius K. (Junius Ku), 1979-
Cyhoeddwyd: (2014)

Perturbation stability for approximate MAP inference
gan: Lang, Hunter(Hunter J.)
Cyhoeddwyd: (2019)

W-SPSA : an Efficient Stochastic Approximation Algorithm for the off-line calibration of Dynamic Traffic Assignment models
gan: Lu, Lu, S.M. Massachusetts Institute of Technology
Cyhoeddwyd: (2014)

Sign-problem free quantum stochastic series expansion algorithm on a quantum computer
gan: Tan, Kok Chuan, et al.
Cyhoeddwyd: (2023)

Contraction maps and applications to the analysis of iterative algorithms
gan: Zampetakis, Emmanouil
Cyhoeddwyd: (2017)

Application of stochastic approximation methods to system optimization
Cyhoeddwyd: (2004)

Segmented approximation and analysis of stochastic processes.
gan: Akant, Adnan.
Cyhoeddwyd: (2023)

The topological q-expansion principle
gan: Laures, Gerd
Cyhoeddwyd: (2007)

Approximation algorithms for disjoint paths problems
gan: Kleinberg, Jon M
Cyhoeddwyd: (2005)

Approximation algorithms for capacitated stochastic inventory systems with setup costs
gan: Shi, Cong, et al.
Cyhoeddwyd: (2017)

Q&A: Expansion microscopy
gan: Gao, Ruixuan, et al.
Cyhoeddwyd: (2017)

A robust recurrent simultaneous perturbation stochastic approximation training algorithm for recurrent neural networks
gan: Song, Qing, et al.
Cyhoeddwyd: (2014)

Simple and accurate approximations for marcum Q-function
gan: Feng, Lin
Cyhoeddwyd: (2023)

Approximation algorithms for combinatorial optimization under uncertainty
gan: Minkoff, Maria, 1976-
Cyhoeddwyd: (2014)

Approximation algorithms for grammar-based data compression
gan: Lehman, Eric (Eric Allen), 1970-
Cyhoeddwyd: (2014)

A family of algorithms for approximate Bayesian inference
gan: Minka, Thomas Peter
Cyhoeddwyd: (2014)

Algorithms and approximation schemes for machine scheduling problems
gan: Sengupta, Sudipta, 1974-
Cyhoeddwyd: (2013)

A robust recurrent simultaneous perturbation stochastic approximation training algorithm for recurrent neural networks
gan: Xu, Zhao, et al.
Cyhoeddwyd: (2013)

Approximation Algorithms for the Stochastic Lot-Sizing Problem with Order Lead Times
gan: Levi, Retsef, et al.
Cyhoeddwyd: (2014)

Stochastic and shortest path games : theory and algorithms
gan: Patek, Stephen D. (Stephen David)
Cyhoeddwyd: (2005)

Product expansions of q-character polynomials
gan: Balachandran, Adithya, et al.
Cyhoeddwyd: (2023)

A learning method for the approximation of discontinuous functions for stochastic simulations
gan: Gorodetsky, Alex Arkady
Cyhoeddwyd: (2013)

Approximation algorithms for multicommodity flow and shop scheduling problems
gan: Stein, Clifford
Cyhoeddwyd: (2005)

Construction of nonlinear filter algorithms using the saddlepoint approximation
gan: Amayo, Esosa O
Cyhoeddwyd: (2008)

Faster streaming algorithms for low-rank matrix approximations
gan: Galvin, Timothy Matthew
Cyhoeddwyd: (2014)

On Boundedness of Q-Learning Iterates for Stochastic Shortest Path Problems
gan: Yu, Huizhen, et al.
Cyhoeddwyd: (2015)

In-situ wafer uniformity estimation using principal component analysis and function approximation methods
gan: White, David A. (David Allan), 1966-
Cyhoeddwyd: (2005)

Learning algorithms in fuzzy cognitive maps
gan: Song, Hengjie
Cyhoeddwyd: (2014)

Designing AIWolf agents by rule-based algorithm and by deep Q-learning
gan: Zhang, Shengjing
Cyhoeddwyd: (2021)

Gamma approximation of stochastic integrals
gan: Nicholas, Susanto Tjandra
Cyhoeddwyd: (2019)

MAP approximation to the variational Bayes Gaussian mixture model and application
gan: Lim, Kart-Leong, et al.
Cyhoeddwyd: (2020)

Formulations and algorithms for network design problems with connectivity requirements
gan: Raghavan, S., 1966-
Cyhoeddwyd: (2005)

Interactive proof system variants and approximation algorithms for optical networks
gan: Sundaram, Ravi, 1968-
Cyhoeddwyd: (2008)

Approximation algorithms for low-distortion embeddings into low-dimensional spaces
gan: Sidiropoulos, Anastasios
Cyhoeddwyd: (2006)