Adaptive linear quadratic control using policy iteration

Proceedings of the American Control Conference

Volumn 3, Issue , 1994, Pages 3475-3479

  Bradtke, Steven J ^a   Ydstie, B Erik ^a  

^a UNIVERSITY OF MASSACHUSETTS   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; CONVERGENCE OF NUMERICAL METHODS; DISCRETE TIME CONTROL SYSTEMS; DYNAMIC PROGRAMMING; EIGENVALUES AND EIGENFUNCTIONS; HEURISTIC PROGRAMMING; LEARNING SYSTEMS; MATHEMATICAL MODELS; MULTIVARIABLE CONTROL SYSTEMS; OPTIMAL CONTROL SYSTEMS; SYSTEM STABILITY;

ADAPTIVE LINEAR QUADRATIC CONTROL; CONTINUOUS PROBLEM; FEEDBACK CONTROL; LINEAR QUADRATIC REGULATION; PARTICULAR SIGNAL VECTOR; Q LEARNING; REINFORCEMENT LEARNING ALGORITHMS; TEMPORAL DIFFERENCE METHODS;

ADAPTIVE CONTROL SYSTEMS;

EID: 0028584964     PISSN: 07431619     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)