H∞ optimal control of unknown linear discrete-time systems: An off-policy reinforcement learning approach

2015 IEEE 7th International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM) ◽

10.1109/iccis.2015.7274545 ◽

2015 ◽

Author(s):

Bahare Kiumarsi ◽

Hamidreza Modares ◽

Frank L. Lewis ◽

Zhong-Ping Jiang

Keyword(s):

Optimal Control ◽

Reinforcement Learning ◽

Discrete Time ◽

Learning Approach ◽

Discrete Time Systems ◽

Download Full-text

Reinforcement learning and optimal control of discrete-time systems: Using natural decision methods to design optimal adaptive controllers

Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles ◽

10.1049/pbce081e_ch2 ◽

2013 ◽

pp. 9-47

Keyword(s):

Optimal Control ◽

Reinforcement Learning ◽

Discrete Time ◽

Adaptive Controllers ◽

Discrete Time Systems ◽

Decision Methods ◽

Download Full-text

Generalized Policy Iteration-based Reinforcement Learning Algorithm for Optimal Control of Unknown Discrete-time Systems

10.1109/ccdc52312.2021.9601467 ◽

2021 ◽

Author(s):

Mingduo Lin ◽

Bo Zhao ◽

Derong Liu ◽

Xi Liu ◽

Fangchao Luo

Keyword(s):

Optimal Control ◽

Reinforcement Learning ◽

Discrete Time ◽

Learning Algorithm ◽

Policy Iteration ◽

Discrete Time Systems ◽

Time Systems ◽

Reinforcement Learning Algorithm

Download Full-text

Reinforcement learning-based optimal control considering L computation time delay of linear discrete-time systems

2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) ◽

10.1109/adprl.2014.7010632 ◽

2014 ◽

Author(s):

Taishi Fujita ◽

Toshimitu Ushio

Keyword(s):

Optimal Control ◽

Reinforcement Learning ◽

Discrete Time ◽

Computation Time ◽

Discrete Time Systems ◽

Download Full-text

A Class of Optimal Control Problem for Stochastic Discrete-Time Systems with Average Reward Reinforcement Learning

2021 4th IEEE International Conference on Industrial Cyber-Physical Systems (ICPS) ◽

10.1109/icps49255.2021.9468152 ◽

2021 ◽

Author(s):

Yifan Hu ◽

Junjie Fu ◽

Yuezu Lv

Keyword(s):

Optimal Control ◽

Reinforcement Learning ◽

Optimal Control Problem ◽

Control Problem ◽

Discrete Time ◽

Average Reward ◽

Discrete Time Systems ◽

Download Full-text

Closed-loop Solution to Optimal Control for Discrete-Time Systems with Final State Constraints

2020 IEEE 16th International Conference on Control & Automation (ICCA) ◽

10.1109/icca51439.2020.9264585 ◽

2020 ◽

Author(s):

Qichao Sun ◽

Juanjuan Xu ◽

Huanshui Zhang

Keyword(s):

Optimal Control ◽

Discrete Time ◽

Closed Loop ◽

State Constraints ◽

Final State ◽

Discrete Time Systems ◽

Download Full-text

Improved Adaptive Critic for Neural Optimal Control of Constrained Nonlinear Discrete-Time Systems

2020 39th Chinese Control Conference (CCC) ◽

10.23919/ccc50068.2020.9189611 ◽

2020 ◽

Author(s):

Mingming Zhao ◽

Ding Wang ◽

Mingming Ha

Keyword(s):

Optimal Control ◽

Discrete Time ◽

Adaptive Critic ◽

Discrete Time Systems ◽

Download Full-text

Output Feedback Controller for a Class of Unknown Nonlinear Discrete Time Systems Using Fuzzy Rules Emulated Networks and Reinforcement Learning

Fuzzy Information and Engineering ◽

10.1080/16168658.2021.1943887 ◽

2021 ◽

pp. 1-23

Author(s):

C. Treesatayapun

Keyword(s):

Reinforcement Learning ◽

Discrete Time ◽

Output Feedback ◽

Feedback Controller ◽

Fuzzy Rules ◽

Output Feedback Controller ◽

Discrete Time Systems ◽

Download Full-text

Decentralized nearly optimal control of a class of interconnected nonlinear discrete-time systems by using online Hamilton-Bellman-Jacobi formulation

The 2010 International Joint Conference on Neural Networks (IJCNN) ◽

10.1109/ijcnn.2010.5596704 ◽

2010 ◽

Author(s):

S. Mehraeen ◽

S. Jagannathan

Keyword(s):

Optimal Control ◽

Discrete Time ◽

Discrete Time Systems ◽

Time Systems ◽

Jacobi Formulation

Download Full-text

Adaptive Reinforcement Learning Control Based on Neural Approximation for Nonlinear Discrete-Time Systems With Unknown Nonaffine Dead-Zone Input

IEEE Transactions on Neural Networks and Learning Systems ◽

10.1109/tnnls.2018.2844165 ◽

2019 ◽

Vol 30 (1) ◽

pp. 295-305 ◽

Author(s):

Yan-Jun Liu ◽

Shu Li ◽

Shaocheng Tong ◽

C. L. Philip Chen

Keyword(s):

Reinforcement Learning ◽

Discrete Time ◽

Dead Zone ◽

Learning Control ◽

Discrete Time Systems ◽

Download Full-text

Optimal Control and Estimation for Discrete-time Systems

Design of Observer-based Compensators ◽

10.1007/978-1-84882-537-6_11 ◽

2009 ◽

pp. 225-265

Keyword(s):

Optimal Control ◽

Discrete Time ◽

Discrete Time Systems ◽

Download Full-text