|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Hybrid MDP based integrated hierarchical Q-learning显示文摘As a widely used reinforcement learning method,Q-learning is bedeviled by the curse of dimensionality:The computational complexity grows dramatically with the size of state-action space.To combat this difficulty,an integrated hierarchical Q-learning framework is proposed based on the hybrid Markov decision process (MDP) using temporal abstraction instead of the simple MDP.The learning process is naturally organized into multiple levels of learning,e.g.,quantitative (lower) level and qualitative (upper) level,which are modeled as MDP and semi-MDP (SMDP),respectively.This hierarchical control architecture constitutes a hybrid MDP as the model of hierarchical Q-learning,which bridges the two levels of learning.The proposed hierarchical Q-learning can scale up very well and speed up learning with the upper level learning process.Hence this approach is an effective integral learning and control scheme for complex problems.Several experiments are carried out using a puzzle problem in a gridworld environment and a navigation control problem for a mobile robot.The experimental results demonstrate the effectiveness and efficiency of the proposed approach. | CHEN ChunLin DONG DaoYi LI Han-Xiong TARN Tzyh-Jong | 2011 | Science China(Information Sciences)2011，54，11： | 9 |
| 2 | Periodic output feedback stabilization of neutral systems 显示文摘 | Tarn T J Yang T Zeng X | 1996 | IEEE Tran Automat Contr1996，41，4： | 2 |
| 3 | The modelling of quantum control systems显示文摘High-performance control of quantum dynamics is key to the development of quantum technologies.From quantum-state engineering to quantum metrology,theory and practice of quantum control enable robust and cheaper technologies for future industrial applications.Starting from fundamental matter–field interactions, we overview various approaches to modelling quantum control systems, in which control can be implemented by either changing field or material properties. These models are built in time or frequency domain and can be interconnected to form quantum feedback networks. This review can be taken as a useful reference for engineers to understand the quantum physics behind, or for physicists to resolve control problems from a control engineering point of view. | Wenbin Dong Rebing Wu Xiaohu Yuan Chunwen Li Tzyh-Jong Tarn | 2015 | Science Bulletin2015，60，17： | 2 |
| 4 | Hepatitis B virus X protein activates the p38 mitogen-activated protein kinase pathway in dedifferentiated hepatocytes 显示文摘 | Tarn C Zou L Hullinger RL | 2002 | J Viros2002，76，19： | 1 |
| 5 | A role for transportin in deposition of TTP to cytoplasmic RNA granules and mRNA decay显示文摘 | CHANG W L TARN W Y | | 0，，19： | 1 |
| 6 | Perfectionism and Task Performance:Time on Task Mediates the Perfectionistic Strivings-performance Relationship显示文摘 | Joachim Stoeber Daryl Chesterman Terri-Anne Tarn | | 0，，： | 1 |
| 7 | A dynamic model of underwater vehicle with a robotic manipulator using Kane's method显示文摘 | TARN T J SHOULTS G A YANG S P | 1996 | Autonomous Robotics1996，3，： | 1 |
| 8 | A hybrid switching control strategy for nonlinear and underactuated mechanical systems显示文摘 | Tarn Tzyh-jong | 2003 | IEEE Transactions on Automatic Control2003，48，10： | 1 |
| 9 | Analysis of cracked plates with a bonded patch显示文摘 | Tarn J Q Shek K L | 1991 | Engineering Fracture Mechanics1991，40，6： | 1 |
| 10 | Intelligent planning and control for muhirobot coordination: An Event-Based Applroach显示文摘 | Xi N Tarn T J Bejczy A K | 1996 | IEEE Transactions on Robotics and Automation1996，12，3： | 1 |
| 11 | Integration of task scheduling, action planning, and control in robotic manufacturing显示文摘 | Song M -J Tarn T Xi N | 2000 | IEEE Transactions on Robotics and Automation2000，88，： | 1 |
| 12 | Polymyxin B: similarities to and differences 显示文摘 | Kwa A Kasiakou SK Tarn VH et a1 | 2007 | Expert Rev Anti Infect Thcr2007，5，5： | 1 |
| 13 | Exponential observers for nonlinear dynamic systems显示文摘 | KOU S R ELLIOTT D L TARN T J | 1975 | Information and Control1975，29，： | 1 |
| 14 | Sensor-Based Hybrid Position/force Control of A Robot Manipulator in an Uncalibrated Environment显示文摘 | Xiao D Ghosh B K Xi N and Tarn T J | 2000 | IEEE Trans on Control System Technology2000，8，4： | 1 |
| 15 | Hepatitis B virus X protein differentially regulates cell cycle progression in X-transforming versus nontransforming hepatocyte (AML12) cell lines显示文摘 | Lee S Tarn C Wang WH | 2002 | J Biol Chem2002，277，10： | 1 |
| 16 | Laminated composite tubes under extension, torsion, bending, shearing and pressuring: a state space approach显示文摘 | Jiann-Quo Tarn Yung-Ming Wang | 2001 | International Journal of Solids and Structures2001，，50： | 1 |
| 17 | Exponential observers for nonlinear dynamic systems 显示文摘 | KOU S R ELLIOTT D TARN T J | 1975 | Information and Control1975，29，3： | 1 |
| 18 | Semiglobal L2 performance bounds for dislurbance attenuation in nonlinear systems 显示文摘 | ISIDORI A SCHWARTS B TARN T J | 1999 | IEEE Trans on Automatic Control1999，44，8： | 1 |
| 19 | Location of canal isthmus and accessory canals in the mesiobuccal root of maxillary first permanent molars显示文摘 | Tarn A Yu DC | 2002 | J Can Dent Assoc2002，68，1： | 1 |
| 20 | Global linearization of control systems via feedback显示文摘 | CHEN D TARN T J ISIDORIA | 1983 | IEEE Transactions on Automatic Control1983，30，8： | 1 |
您所在的机构暂未开通此部分的功能，请联系管理员