Huizhen Yu - RankMe

46 papers A* 2A 2Journal 32Unranked 9

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Quasi-multimodal-based pathophysiological feature learning for retinal disease diagnosis. CoRR Lu Zhang, Huizhen Yu, Zuowei Wang, Fu Gui, Yatu Guo, Wei Zhang, Mengyu Jia
2026	J	`jnl`	Quasi-multimodal-based pathophysiological feature learning for retinal disease diagnosis. Medical Image Anal. Lu Zhang, Huizhen Yu, Zuowei Wang, Fu Gui, Yatu Guo, Wei Zhang, Mengyu Jia
2025	J	`jnl`	Average-reward reinforcement learning in semi-Markov decision processes via relative value iteration. CoRR Huizhen Yu, Yi Wan, Richard S. Sutton
2024	J	`jnl`	Asynchronous Stochastic Approximation and Average-Reward Reinforcement Learning. CoRR Huizhen Yu, Yi Wan, Richard S. Sutton
2024	J	`jnl`	On Convergence of Average-Reward Q-Learning in Weakly Communicating Markov Decision Processes. CoRR Yi Wan, Huizhen Yu, Richard S. Sutton
2024	J	`jnl`	On Strategic Measures and Optimality Properties in Discrete-Time Stochastic Control with Universally Measurable Policies. Math. Oper. Res. Huizhen Yu
2023	J	`jnl`	A Note on Stability in Asynchronous Stochastic Approximation without Communication Delays. CoRR Huizhen Yu, Yi Wan, Richard S. Sutton
2022	J	`jnl`	On Linear Programming for Constrained and Unconstrained Average-Cost Markov Decision Processes with Countable Action Spaces and Strictly Unbounded Costs. Math. Oper. Res. Huizhen Yu
2020	J	`jnl`	Average Cost Optimality Inequality for Markov Decision Processes with Borel Spaces and Universally Measurable Policies. SIAM J. Control. Optim. Huizhen Yu
2020	J	`jnl`	On the Minimum Pair Approach for Average Cost Markov Decision Processes with Countable Discrete Action Spaces and Strictly Unbounded Costs. SIAM J. Control. Optim. Huizhen Yu
2020	—	`conf`	Research on the Structural Impact of the Disappearance of China's Demographic Dividend on the Education Industry. ICETM Huizhen Yu
2018	J	`jnl`	On Generalized Bellman Equations and Temporal-Difference Learning. J. Mach. Learn. Res. Huizhen Yu, Ashique Rupam Mahmood, Richard S. Sutton
2018	J	`jnl`	Two geometric input transformation methods for fast online reinforcement learning with neural nets. CoRR Sina Ghiassian, Huizhen Yu, Banafsheh Rafiee, Richard S. Sutton
2017	J	`jnl`	Multi-step Off-policy Learning Without Importance Sampling Ratios. CoRR Ashique Rupam Mahmood, Huizhen Yu, Richard S. Sutton
2017	J	`jnl`	On Convergence of some Gradient-based Temporal-Differences Algorithms for Off-Policy Learning. CoRR Huizhen Yu
2017	—	`conf`	On Generalized Bellman Equations and Temporal-Difference Learning. Canadian AI Huizhen Yu, Ashique Rupam Mahmood, Richard S. Sutton
2017	J	`jnl`	On Generalized Bellman Equations and Temporal-Difference Learning. CoRR Huizhen Yu, Ashique Rupam Mahmood, Richard S. Sutton
2016	J	`jnl`	Some Simulation Results for Emphatic Temporal-Difference Learning Algorithms. CoRR Huizhen Yu
2016	J	`jnl`	Weak Convergence Properties of Constrained Emphatic Temporal-difference Learning with Constant and Slowly Diminishing Stepsize. J. Mach. Learn. Res. Huizhen Yu
2015	J	`jnl`	A Mixed Value and Policy Iteration Method for Stochastic Control with Universally Measurable Policies. Math. Oper. Res. Huizhen Yu, Dimitri P. Bertsekas
2015	J	`jnl`	Emphatic Temporal-Difference Learning. CoRR Ashique Rupam Mahmood, Huizhen Yu, Martha White, Richard S. Sutton
2015	A*	`conf`	On Convergence of Emphatic Temporal-Difference Learning. COLT Huizhen Yu
2015	J	`jnl`	On Convergence of Emphatic Temporal-Difference Learning. CoRR Huizhen Yu
2015	J	`jnl`	On Convergence of Value Iteration for a Class of Total Cost Markov Decision Processes. SIAM J. Control. Optim. Huizhen Yu
2015	J	`jnl`	Weak Convergence Properties of Constrained Emphatic Temporal-difference Learning with Constant and Slowly Diminishing Stepsize. CoRR Huizhen Yu
2013	J	`jnl`	On Boundedness of Q-Learning Iterates for Stochastic Shortest Path Problems. Math. Oper. Res. Huizhen Yu, Dimitri P. Bertsekas
2013	J	`jnl`	Q-learning and policy iteration algorithms for stochastic shortest path problems. Ann. Oper. Res. Huizhen Yu, Dimitri P. Bertsekas
2012	J	`jnl`	A Function Approximation Approach to Estimation of Policy Gradient for POMDP with Structured Policies CoRR Huizhen Yu
2012	J	`jnl`	Discretized Approximations for POMDP with Average Cost CoRR Huizhen Yu, Dimitri P. Bertsekas
2012	J	`jnl`	Least Squares Temporal Difference Methods: An Analysis under General Conditions. SIAM J. Control. Optim. Huizhen Yu
2012	J	`jnl`	Q-Learning and Enhanced Policy Iteration in Discounted Dynamic Programming. Math. Oper. Res. Dimitri P. Bertsekas, Huizhen Yu
2011	J	`jnl`	A Unifying Polyhedral Approximation Framework for Convex Optimization. SIAM J. Optim. Dimitri P. Bertsekas, Huizhen Yu
2010	A*	`conf`	Convergence of Least Squares Temporal Difference Methods Under General Conditions. ICML Huizhen Yu
2010	—	`conf`	Distributed asynchronous policy iteration in dynamic programming. Allerton Dimitri P. Bertsekas, Huizhen Yu
2010	J	`jnl`	Error Bounds for Approximations from Projected Linear Equations. Math. Oper. Res. Huizhen Yu, Dimitri P. Bertsekas
2010	—	`conf`	Q-learning and enhanced policy iteration in discounted dynamic programming. CDC Dimitri P. Bertsekas, Huizhen Yu
2009	—	`conf`	Basis function adaptation methods for cost approximation in MDP. ADPRL Huizhen Yu, Dimitri P. Bertsekas
2009	J	`jnl`	Convergence Results for Some Temporal Difference Methods Based on Least Squares. IEEE Trans. Autom. Control. Huizhen Yu, Dimitri P. Bertsekas
2008	—	`conf`	Efficient Discriminative Training Method for Structured Predictions. MLG@ICML Huizhen Yu, Dimitri P. Bertsekas, Juho Rousu
2008	—	`conf`	New Error Bounds for Approximations from Projected Linear Equations. EWRL Huizhen Yu, Dimitri P. Bertsekas
2008	—	`conf`	New error bounds for approximations from projected linear equations. Allerton Huizhen Yu, Dimitri P. Bertsekas
2008	J	`jnl`	On Near Optimality of the Set of Finite-State Controllers for Average Cost POMDP. Math. Oper. Res. Huizhen Yu, Dimitri P. Bertsekas
2006	—	`—`	Approximate solution methods for POMDP and POSMDP. Huizhen Yu
2005	A	`conf`	A Function Approximation Approach to Estimation of Policy Gradient for POMDP with Structured Policies. UAI Huizhen Yu
2004	A	`conf`	Discretized Approximations for POMDP with Average Cost. UAI Huizhen Yu, Dimitri P. Bertsekas
2001	—	`conf`	Combining Configurational and Statistical Approaches in Image Retrieval. IEEE Pacific Rim Conference on Multimedia Huizhen Yu, W. Eric L. Grimson