Eigenfunction approximation methods for linearly-solvable optimal control problems

2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings

Volumn , Issue , 2009, Pages 161-168

  Todorov, Emanuel ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION METHODS; CONTROL PROBLEMS; EIGEN FUNCTION; EIGENVECTOR; ELLIPTIC PDES; FUNCTION APPROXIMATION; GENERAL CLASS; GUARANTEED CONVERGENCE; INTEGRAL OPERATORS; LEVENBERG-MARQUARDT MINIMIZATION; LINEAR OPERATORS; NUMERICAL RESULTS; OPTIMAL CONTROL PROBLEM; REGION OF INTEREST; STATE SPACE; STOCHASTIC OPTIMAL CONTROL PROBLEM; TEST PROBLEM; TIME AXIS; VALUE ITERATION;

APPROXIMATION THEORY; DYNAMIC PROGRAMMING; MATHEMATICAL OPERATORS; OPTIMIZATION; REINFORCEMENT; REINFORCEMENT LEARNING; SET THEORY; SYSTEMS ENGINEERING;

EIGENVALUES AND EIGENFUNCTIONS;

EID: 67650469280     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ADPRL.2009.4927540     Document Type: Conference Paper

References (5)

1. H. Kappen. Linear theory for control of nonlinear stochastic systems. Physical Review Letters, 95, 2005.
2. H.J. Kushner and P. Dupuis. Numerical Methods for Stochastic Optimal Control Problems in Continuous Time. Springer, New York, 2001.
3. S. Mitter and N. Newton. A variational approach to nonlinear estimation. SIAM J Control Opt, 42:1813-1833, 2003.
4. E. Todorov. Linearly-solvable Markov decision problems. Advances in Neural Information Processing Systems, 2006.
5. E. Todorov. General duality between optimal control and estimation. IEEE Conference on Decision and Control, 2008.