Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Huizhen Yu
Observed names:
H. Yu,
Yu, Huizhen,
Yu, Huizhen, Ph. D. Massachusetts Institute of Technology
Institution:
University of Alberta
Observed institutions:
University of Helsinki,
University of Alberta,
Helsinki Institute for Information Technology,
Massachusetts Institute of Technology
ORCID:
0000-0002-3673-0094
Observed ORCID:
0000-0002-3673-0094
OpenAlex ID:
A5014937312
Convergence Results for Some Temporal Difference Methods Based on Least Squares
2009
·
Huizhen Yu
, D.P. Bertsekas
·
IEEE Transactions on Automatic Control
·
100
PDF
Projected equation methods for approximate solution of large linear systems
2008
·
Dimitri P. Bertsekas
, Huizhen Yu
·
Journal of Computational and Applied Mathematics
·
62
On Convergence of Emphatic Temporal-Difference Learning
2015
·
Yu, Huizhen
·
arXiv (Cornell University)
·
49
PDF
A Unifying Polyhedral Approximation Framework for Convex Optimization
2011
·
Dimitri P. Bertsekas
, Huizhen Yu
·
SIAM Journal on Optimization
·
45
Least Squares Temporal Difference Methods: An Analysis under General Conditions
2012
·
Huizhen Yu
·
SIAM Journal on Control and Optimization
·
43
PDF
Discretized Approximations for POMDP with Average Cost
2012
·
Yu, Huizhen
, Bertsekas, Dimitri
·
arXiv (Cornell University)
·
41
PDF
On Near Optimality of the Set of Finite-State Controllers for Average Cost POMDP
2008
·
Huizhen Yu
, Dimitri P. Bertsekas
·
Mathematics of Operations Research
·
41
Q-learning and policy iteration algorithms for stochastic shortest path problems
2012
·
Huizhen Yu
, Dimitri P. Bertsekas
·
Annals of Operations Research
·
40
Q-Learning and Enhanced Policy Iteration in Discounted Dynamic Programming
2012
·
Dimitri P. Bertsekas
, Huizhen Yu
·
Mathematics of Operations Research
·
38
Error Bounds for Approximations from Projected Linear Equations
2010
·
Huizhen Yu
, Dimitri P. Bertsekas
·
Mathematics of Operations Research
·
38
Basis function adaptation methods for cost approximation in MDP
2009
·
Huizhen Yu
, Dimitri P. Bertsekas
·
IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning
·
38
PDF
Convergence of Least Squares Temporal Difference Methods Under General Conditions
2010
·
Huizhen Yu
·
Työväentutkimus Vuosikirja
·
33
PDF
Distributed asynchronous policy iteration in dynamic programming
2010
·
Dimitri P. Bertsekas
, Huizhen Yu
·
Allerton Conference on Communication, Control, and Computing
·
31
Q-learning algorithms for optimal stopping based on least squares
2007
·
Huizhen Yu
, Dimitri P. Bertsekas
·
European Control Conference (ECC)
·
30
Approximate solution methods for partially observable markov and semi-markov decision processes
2006
·
Dimitri P. Bertsekas
, Huizhen Yu
·
30
Weak Convergence Properties of Constrained Emphatic Temporal-difference Learning with Constant and Slowly Diminishing Stepsize
2015
·
Yu, Huizhen
·
arXiv (Cornell University)
·
22
PDF
On Convergence of some Gradient-based Temporal-Differences Algorithms for Off-Policy Learning
2017
·
Yu, Huizhen
·
arXiv (Cornell University)
·
21
PDF
Multi-step Off-policy Learning Without Importance Sampling Ratios
2017
·
Mahmood, Ashique Rupam
, Yu, Huizhen
, et al.
·
arXiv (Cornell University)
·
21
PDF
Markov Random Fields
2010
·
Huizhen Yu
, Huizhen Yu
·
21
A Least Squares Q-Learning Algorithm for Optimal Stopping Problems
2007
·
Huizhen Yu
, Dimitri P. Bertsekas
·
21
On Boundedness of Q-Learning Iterates for Stochastic Shortest Path Problems
2012
·
Huizhen Yu
, Dimitri P. Bertsekas
·
Mathematics of Operations Research
·
19
Emphatic Temporal-Difference Learning
2015
·
Mahmood, A. Rupam
, Yu, Huizhen
, et al.
·
arXiv (Cornell University)
·
18
PDF
On Generalized Bellman Equations and Temporal-Difference Learning
2017
·
Huizhen Yu
, Ashique Rupam Mahmood
, et al.
·
Lecture notes in computer science
·
17
PDF
Q-learning and enhanced policy iteration in discounted dynamic programming
2010
·
Dimitri P. Bertsekas
, Huizhen Yu
·
Proceedings of the IEEE Conference on Decision & Control, including the Symposium on Adaptive Processes
·
15
A Mixed Value and Policy Iteration Method for Stochastic Control with Universally Measurable Policies
2015
·
Huizhen Yu
, Dimitri P. Bertsekas
·
Mathematics of Operations Research
·
14
PDF
Show more works
View as search
Works count:
65
Citation count:
954
H-index:
21
I10-index:
28
Year
Topic
Type
