Path integral-based stochastic optimal control for rigid body dynamics

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

Volumn , Issue , 2009, Pages 219-225

  Theodorou, E A ^a   Buchli, J ^a   Schaal, S ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

CONTROL SPACES; FEYNMAN-KAC FORMULA; GENERAL CLASS; HAMILTON-JACOBI-BELLMAN EQUATIONS; HJB EQUATIONS; INVERSE DYNAMICS CONTROLLERS; LOGARITHMIC TRANSFORMATIONS; NON-LINEAR STOCHASTIC SYSTEMS; OPTIMAL CONTROLS; OPTIMAL VALUE FUNCTIONS; PATH INTEGRAL; RIGIDBODY DYNAMICS; SECOND-ORDER PARTIAL DIFFERENTIAL EQUATION; STATE-DEPENDENT; STOCHASTIC OPTIMAL CONTROL; THEORETICAL RESULT; TIME INVARIANTS; TRANSITION MATRICES;

DYNAMIC PROGRAMMING; LINEARIZATION; OPTIMAL CONTROL SYSTEMS; OPTIMIZATION; PARTIAL DIFFERENTIAL EQUATIONS; QUANTUM THEORY; REINFORCEMENT; REINFORCEMENT LEARNING; STOCHASTIC SYSTEMS; SYSTEMS ENGINEERING;

STOCHASTIC CONTROL SYSTEMS;

EID: 67650458713     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ADPRL.2009.4927548     Document Type: Conference Paper

References (16)

1. H. Kappen, "A linear theory for control of non-linear stochastic systems," Physical Review Letters, 2005.
2. H. Kappen, "Path integrals and symmetry breaking for optimal control," Journal of Statistical Mechanics, Vol. 11, 2005. (Pubitemid 41787676)
3. B. Oksendal, Stochastic Differential Equations, 2nd ed. Springer Verlag, 1995.
4. R. Stengel, Optimal Control and Estimation. Dover Publications, New York, 1993.
5. W. Li and E. Todorov, "Iterative linear quadratic regulator desing for nonlinear biological systems," in Proceedings of the 1th international conference on Informatics and Control, Automation and Robotics, 2004, pp. 222-229.
6. E. Todorov, "Iterative optimal control and estimation design for nonlinear systems," in Proceedings of the 45th IEEE control and decision conference, 2006, pp. 3242-3247. (Pubitemid 351284068)
7. C. Atkeson and B. Stephens, "Minimax differential dynamic programming: application to a biped walking robot," in Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vol. 2, 2003, pp. 1927-1932.
8. J. Morimoto and C. Zeglin, G. Atkeson, "Random sampling of states in dynamic programming," in Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS), 2007.
9. J. Peters and S. Schaal, "Reinforcement learning of motor skills with policy gradients," Neural Networks, Vol. 21, pp. 682-697, 2008.
10. J. Peters and S. Schaal, "Using reward-weighted regression for reinforcement learning of task space control," in Proceedings of the 2007 IEEE Internatinal Symposium on Approximate Dynamic Programming and Reinforcement Learning, 2007. (Pubitemid 47431394)
11. J. Peters and S. Schaal, "Reinforcement learning by reward-weighted regression for operational space control," in Proceedings of the International Conference on Machine Learning (ICML), 2007.
12. B. Balaij, "Estimation of indirectly observable langevin states: path integral solution using statistical physics methods," Journal of Statistical Mechanics, p. P01014, 2008.
13. B. Balaij, "Universal nonlinear filtering using path integrals I: The continuous - discrete model with additive noise," arXiv, 2006.
14. B. Balaij, "Universal nonlinear filtering using path integrals II: The continuous - continuous model with additive noise," arXiv, 2008.
15. W. Fleming, "Exit probabilities and optimal stochastic control," Applied Math. Optim., pp. 329-346, 1978. (Pubitemid 9403108)
16. W. Fleming and H. Soner, Controlled Markov Processes and Viscosity Solutions, 4th ed. Springer Verlag, 2006.