On stochastic optimal control and reinforcement learning by approximate inference

Robotics: Science and Systems

Volumn 8, Issue , 2013, Pages 353-360

  Rawlik, Konrad ^a   Toussaint, Marc ^b   Vijayakumar, Sethu ^a  

^a UNIVERSITY OF EDINBURGH   (United Kingdom)

^b FREIE UNIVERSITÄT BERLIN   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 84959314908     PISSN: None     EISSN: 2330765X     Source Type: Conference Proceeding    
DOI: 10.15607/rss.2012.viii.045     Document Type: Conference Paper

References (26)

1. C. M. Bishop. Pattern recognition and machine learning. Springer, 2006.
2. D. Braun, M. Howard, and S. Vijayakumar. Exploiting variable stiffness in explosive movement tasks. In R:SS, 2011.
3. J.L. van den Broek, W.A.J.J. Wiegerinck, and H.J. Kappen. Risk sensitive path integral control. In UAI, 2010.
4. P. Dayan and G. E. Hinton. Using EM for reinforcement learning. Neural Computation, 9:271-278, 1997.
5. A.M. Gheshlaghi et al. Dynamic policy programming with function approximation. In AISTATS, 2011.
6. D. Mitrovic et al. Optimal feedback control for anthropomorphic manipulators. In ICRA, 2010.
7. E. A. Theodorou et al. Learning policy improvements with path integrals. In AISTATS, 2010.
8. S.I. Marcus et al. Risk sensitive markov decision processes. Systems and control in the 21st century, 1997.
9. A. Gunawardana and W. Byrne. Convergence theorems for generalized alternating minimization procedures. J. of Machine Learning Research, 6:2049-2073, 2005.
10. B. Kappen, V. Gomez, and M. Opper. Optimal control as a graphical model inference problem. arXiv:0901.0633v2, 2009.
11. H. J. Kappen. Path integrals and symmetry breaking for optimal control theory. J. of Statistical Mechanics: Theory and Experiment, page 11011ff, 2005.
12. J. Kivinen and M. Warmuth. Exponentiated gradient versus gradient descent for linear predictors. Information and Computation, 132:1-64, 1997.
13. W. Li and E. Todorov. An iterative optimal control and estimation design for nonlinear stochastic system. In CDC, 2006.
14. D. Mitrovic, S. Klanke, and S. Vijayakumar. Adaptive optimal control for redundantly actuated arms. In SAB, 2008.
15. J. Nakanishi, K. Rawlik, and S. Vijayakumar. Stiffness and temporal optimization in periodic movements: An optimal control approach. In IROS, 2011.
16. J. Peters, S. Vijayakumar, and S. Schaal. Reinforcement learning for humanoid robotics. In Humanoids, 2003.
17. K. Rawlik, M. Toussaint, and S. Vijayakumar. An approximate inference approach to temporal optimization in optimal control. In NIPS, 2010.
18. M. Riedmiller, J. Peters, and S. Schaal. Evaluation of policy gradient methods and variants on the cart-pole benchmark. In IEEE ADPRL, 2007.
19. P. N. Sabes and M. I. Jordan. Reinforcement learning by probability matching. In NIPS, 1996.
20. R. F. Stengel. Optimal Control and Estimation. Dover Publications, 1986.
21. R.S. Sutton and A.G. Barto. Reinforcement Learning. MIT Press, Cambridge, 1998.
22. E. Todorov. Efficient computation of optimal actions. PNAS, 106:11478-11483, 2009.
23. E. Todorov and M. Jordan. Optimal feedback control as a theory of motor coordination. Nature Neuroscience, 5:1226-1235, 2002.
24. M. Toussaint. Robot trajectory optimization using approximate inference. In ICML, 2009.
25. M. Toussaint and A. Storkey. Probabilistic inference for solving discrete and continuous state markov decision processes. In ICML, 2006.
26. D. Zarubin, V. Ivan, M. Toussaint, T. Komura, and S. Vijayakumar. Hierarchical motion planning in topological representations. In R:SS, 2012.