PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

EPrints submitted by Huizhen Yu

Click here to see user's record.

Number of EPrints submitted by this user: 13

A Least Squares Q-Learning Algorithm for Optimal Stopping Problems
Huizhen Yu and Dimitri Bertsekas
(2006) Technical Report. Lab for Information and Decision Systems (LIDS), MIT.

Q-learning Algorithms for Optimal Stopping Based on Least Squares
Huizhen Yu and Dimitri Bertsekas
In: European Control Conference (ECC'07), 2-5 Jul 2007, Kos, Greece.

Projected Equation Methods for Approximate Solution of Large Linear Systems
Dimitri Bertsekas and Huizhen Yu
Journal of Computational and Applied Mathematics Volume 227, Number 1, pp. 27-50, 2009.

An Efficient Method for Large Margin Parameter Optimization in Structured Prediction Problems
Huizhen Yu and Juho Rousu
(2007) Technical Report. Department of Computer Science.

Basis Function Adaptation Methods for Cost Approximation in MDP
Huizhen Yu and Dimitri Bertsekas
In: IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) 2009, Nashville, USA(2009).

Error Bounds for Approximations from Projected Linear Equations
Huizhen Yu and Dimitri Bertsekas
Mathematics of Operations Research 2008.

A Unifying Polyhedral Approximation Framework for Convex Optimization
Dimitri Bertsekas and Huizhen Yu
SIAM journal on Optimization 2011.

Convergence Results for Some Temporal Difference Methods Based on Least Squares
Huizhen Yu and Dimitri Bertsekas
IEEE Trans. Automatic Control Volume 54, Number 7, pp. 1515-1531, 2009.

Convergence of Least Squares Temporal Difference Methods Under General Conditions
Huizhen Yu
In: ICML 2010(2010).

Least Squares Temporal Difference Methods: An Analysis Under General Conditions
Huizhen Yu
(2010) Technical Report. University of Helsinki.

Distributed Asynchronous Policy Iteration in Dynamic Programming
Dimitri Bertsekas and Huizhen Yu
In: The 48th Allerton Conference on Communication, Control and Computing(2010).

Q-Learning and Enhanced Policy Iteration in Discounted Dynamic Programming
Dimitri Bertsekas and Huizhen Yu
In: The 49th IEEE Conference on Decision and Control (CDC)(2010).

Q-Learning and Enhanced Policy Iteration in Discounted Dynamic Programming
Dimitri Bertsekas and Huizhen Yu
(2010) Technical Report. University of Helsinki.