Latent Kullback Leibler control for continuous-state systems using probabilistic graphical models

Uncertainty in Artificial Intelligence - Proceedings of the 30th Conference, UAI 2014

Volumn , Issue , 2014, Pages 583-592

  Matsubara, Takamitsu ^a   Gómez, Vicenç ^b,c   Kappen, Hilbert J ^b  

^a NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

^b RADBOUD UNIVERSITY   (Netherlands)

^c UNIVERSITAT POMPEU FABRA   (Spain)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; GRAPHIC METHODS; MARKOV PROCESSES; SPEECH RECOGNITION;

EFFICIENT COMPUTATION; HIDDEN MARKOV MODELS (HMMS); HIGH-DIMENSIONAL; HIGHER-DIMENSIONAL PROBLEMS; LOW-DIMENSIONAL SYSTEMS; PRINCIPAL EIGEN-VECTOR; PROBABILISTIC GRAPHICAL MODELS; ROBOT MOTOR CONTROL;

HIDDEN MARKOV MODELS;

EID: 84923272712     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Doya, K. (2000). Reinforcement learning in continuous time and space. Neural Comput., 12(1):219-245.
2. Ghahramani, Z. and Jordan, M. (1997). Factorial hidden markov models. Mach. Learn., 29(2-3):245-273.
3. Kappen, H. J., Gómez, V., and Opper, M. (2012). Optimal control as a graphical model inference problem. Mach. Learn., 87(2):159-182.
4. Kinjo, K., Uchibe, E., and Doya, K. (2013). Evaluation of linearly solvable Markov decision process with dynamic model learning in a mobile robot navigation task. Front. Neurorobot., 7:1-13.
5. Mitrovic, D., Nagashima, S., Klanke, S., Matsubara, T., and Vijayakumar, S. (2010). Optimal feedback control for anthropomorphic manipulators. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA'10), pages 4143-4150.
6. Murphy, K. P. (2012). Machine Learning: A Probabilistic Perspective. MIT Press.
7. Sugiyama, M., Hachiya, H., Towell, C., and Vijayakumar, S. (2007). Value function approximation on non-linear manifolds for robot motor control. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA'07), pages 1733-1740.
8. Sutton, R. S. and Barto, A. G. (1998). Introduction to Reinforcement Learning. MIT Press, Cambridge, MA, USA, 1st edition.
9. Theodorou, E., Buchli, J., and Schaal, S. (2010). Reinforcement learning of motor skills in high dimensions: A path integral approach. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA'10), pages 2397-2403.
10. Todorov, E. (2006). Linearly-solvable markov decision problems. In Advances in Neural Information Processing Systems (NIPS), pages 1369-1376.
11. Todorov, E. (2009a). Efficient computation of optimal actions. PNAS, 106(28):11478-11483.
12. Todorov, E. (2009b). Eigenfunction approximation methods for linearly-solvable optimal control problems. In Proceedings of the 2nd IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, pages 161-168.
13. Yoshikawa, T. (1990). Foundations of Robotics: Analysis and Control. The MIT Press.
14. Zhong, M. and Todorov, E. (2011a). Aggregation methods for linearly-solvable Markov decision process. In World Congress of the International Federation of Automatic Control, pages 11220-11225.
15. Zhong, M. and Todorov, E. (2011b). Moving least-squares approximations for linearly-solvable stochastic optimal control problems. J. Control. Theory. Appl., 9(3):451-463.