Jun Ma

发表

Convergence Analysis of On-Policy LSPI for Multi-Dimensional Continuous State and Action-Space MDPs and Extension with Orthogonal Polynomial Approximation

Warrren B Powell, Jun Ma, 2010 .

Convergence Analysis of Kernel-based On-policy Approximate Policy Iteration Algorithms for Markov Decision Processes with Continuous, Multidimensional States and Actions

Warrren B Powell, Jun Ma, 2010 .

A review of stochastic algorithms with continuous value function approximation and some new approximate policy iteration algorithms for multidimensional continuous applications

Warrren B Powell, Jun Ma, 2011 .

Convergence Proofs of Least Squares Policy Iteration Algorithm for High-Dimensional Inflnite Horizon Markov Decision Process Problems

Warrren B Powell, Jun Ma, 2008 .

Distributed Predefined-Time Attitude Consensus Control for Multiple Uncertain Spacecraft Formation Flying

Jun Ma, Zeng Wang, Liangmou Hu, 2022, IEEE Access.

Predefined‐time guaranteed performance attitude tracking control for uncertain rigid spacecraft

Jun Ma, Zeng Wang, Chang Wang, 2022, IET Control Theory & Applications.

Deep auto-encoder observer multiple-model fast aircraft actuator fault diagnosis algorithm

Jun Ma, Shihong Ni, Wu-jie Xie, 2017, International Journal of Control, Automation and Systems.

Predefined‐time guaranteed performance attitude takeover control for non‐cooperative spacecraft with uncertainties

Jun Ma, Zeng Wang, Liangmou Hu, 2023, International Journal of Robust and Nonlinear Control.

Deep auto-encoder observer multiple-model fast aircraft actuator fault diagnosis algorithm

Jun Ma, Wenhan Dong, Shihong Ni, 2017, International Journal of Control, Automation and Systems.

A convergent recursive least squares approximate policy iteration algorithm for multi-dimensional Markov decision process with continuous state and action spaces

Warren B. Powell, Jun Ma, Warrren B Powell, 2009, 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning.

Policy-Iteration-Based Finite-Horizon Approximate Dynamic Programming for Continuous-Time Nonlinear Optimal Control

Jun Ma, Jingliang Duan, Jie Li, 2022, IEEE Transactions on Neural Networks and Learning Systems.