Efficient computation of optimal actions

Proceedings of the National Academy of Sciences of the United States of America

Volumn 106, Issue 28, 2009, Pages 11478-11483

  Todorov, Emanuel ^a  

^a UNIVERSITY OF WASHINGTON   (United States)

Author keywords

Action selection; Cost function; Linear Bellman equation; Stochastic optimal control

Indexed keywords

ALGORITHM; ARTICLE; MATHEMATICAL ANALYSIS; PRIORITY JOURNAL; PROBABILITY; SCIENTIFIC LITERATURE; STATISTICS;

ALGORITHMS; INFORMATION SCIENCE; MODELS, THEORETICAL; PROBLEM SOLVING; STOCHASTIC PROCESSES; UNCERTAINTY;

EID: 67650915125     PISSN: 00278424     EISSN: 10916490     Source Type: Journal    
DOI: 10.1073/pnas.0710743106     Document Type: Article

References (19)

1. Todorov E (2004) Optimality principles in sensorimotor control. Nat Neurosci 7(9):907-915.
2. Sutton R, Barto A (1998) Reinforcement Learning: An Introduction (MIT Press, Cambridge MA).
3. Bertsekas D (2001) Dynamic Programming and Optimal Control (Athena Scientific, Bellmont, MA), 2nd Ed.
4. Stengel R (1994) Optimal Control and Estimation (Dover, New York).
5. Korn R (1997) Optimal Portfolios: Stochastic Models for Optimal Investment and Risk Management in Continuous Time (World Scientific, Teaneck, NJ).
6. Fleming W, Mitter S (1982) Optimal control and nonlinear filtering for nondegenerate diffusion processes. Stochastics 8:226-261.
7. Kappen HJ (2005) Linear theory for control of nonlinear stochastic systems. Phys Rev Lett 95:200201.
8. Mitter S, Newton N (2003) A variational approach to nonlinear estimation. SIAM J Control Opt 42:1813-1833.
9. Todorov E (2006) Linearly-solvable Markov decision problems. Adv Neural Information Proc Syst 19:1369-1376.
10. Todorov E (2008) General duality between optimal control and estimation. IEEE Conf Decision Control 47:4286-4292.
11. Todorov E (2009) Eigen-function approximation methods for linearly-solvable optimal control problems, IEEE Int Symp Adapt Dynam Programm Reinforce Learning 2:161-168.
12. Todorov E (2009) Classic Maximum Principles and Estimation-Control Dualities for nonlinear Stochastic Systems, preprint.
13. Todorov E (2009) Compositionality of Optimal Control Laws, preprint.
14. Todorov E (2009) Efficient Algorithms for Inverse Optimal Control, preprint.
15. Watkins C, Dayan P (1992) Q-learning. Mach Learn 8:279-292.
16. Kushner H, Dupuis P (2001) Numerical Methods for Stochastic Optimal Control Problems in Continuous Time (Springer, New York).
17. Bryson A, Ho Y (1969) Applied Optimal Control (Blaisdell Publishing Company, Waltham, MA).
18. Ng A, Russell S (2000) Algorithms for inverse reinforcement learning. Int Conf Mach Learn 17:663-670.
19. Liu K, Hertzmann A, Popovic Z (2005) Learning physics-based motion style with nonlinear inverse optimization. ACM Trans Graphics 24:1071-1081.