Learning complex neural network policies with trajectory optimization

31st International Conference on Machine Learning, ICML 2014

Volumn 3, Issue , 2014, Pages 2411-2420

  Levine, Sergey ^a   Koltun, Vladlen ^b  

^a Stanford University   (United States)

^b ADOBE RESEARCH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; LEARNING SYSTEMS; TRAJECTORIES;

COMPLEX NEURAL NETWORKS; DIRECT POLICY SEARCH; EXPECTED COSTS; HIGH-DIMENSIONAL; LEARNING CONTROLLERS; PUSH RECOVERIES; TRAJECTORY OPTIMIZATION; UNEVEN TERRAIN;

COMPLEX NETWORKS;

EID: 84919913608     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (26)

1. Arnold, W.F. III and Laub, A.J. Generalized eigen problem algorithms and software for algebraic Riccati equations. Proceedings of the IEEE, 72(12), 1984.
2. Boyd, S. and Vandenberghe, L. Convex Optimization. Cambridge University Press, New York, NY, USA, 2004.
3. Deisenroth, M. and Rasmussen, C. PILCO: a model-based and data-efficient approach to policy search. In International Conference on Machine Learning (ICML), 2011.
4. Deisenroth, M., Neumann, G., and Peters, J. A survey on policy search for robotics. Foundations and Trends in Robotics, 2(1-2), 2013.
5. Ijspeert, A., Nakanishi, J., and Schaal, S. Learning attractor landscapes for learning motor primitives. In Advances in Neural Information Processing Systems (NIPS), 2003.
6. Kappen, H. J., Gomez, V., and Opper, M. Optimal control as a graphical model inference problem. Machine Learning, 87(2), 2012.
7. Kober, J. and Peters, J. Learning motor primitives for robotics. In International Conference on Robotics and Automation (ICRA), 2009.
8. Kober, J., Bagnell, J. A., and Peters, J. Reinforcement learning in robotics: A survey. International Journal of Robotic Research, 32(11), 2013.
9. Kolter, J. Z., Jackowski, Z., and Tedrake, R. Design, analysis and learning control of a fully actuated micro wind turbine. In American Control Conference (ACC), 2012.
10. Levine, S. Exploring deep and recurrent architectures for optimal control. In NIPS 2013 Workshop on Deep Learning, 2013.
11. Levine, S. and Koltun, V. Guided policy search. In International Conference on Machine Learning (ICML), 2013a.
12. Levine, S. and Koltun, V. Variational policy search via trajectory optimization. In Advances in Neural Information Processing Systems (NIPS), 2013b.
13. Mordatch, I. and Todorov, E. Combining the benefits of function approximation and trajectory optimization. In Robotics: Science and Systems (RSS), 2014.
14. Paraschos, A., Daniel, C., Peters, J., and Neumann, G. Probabilistic movement primitives. In Advances in Neural Information Processing Systems (NIPS), 2013.
15. Peters, J. and Schaal, S. Applying the episodic natural actor-critic architecture to motor primitive learning. In European Symposium on Artificial Neural Networks (ESANN), 2007.
16. Peters, J. and Schaal, S. Reinforcement learning of motor skills with policy gradients. Neural Networks, 21(4), 2008.
17. Rawlik, K., Toussaint, M., and Vijayakumar, S. On stochastic optimal control and reinforcement learning by approximate inference. In Robotics: Science and Systems (RSS), 2012.
18. Ross, S. and Bagnell, A. Agnostic system identification for model-based reinforcement learning. In International Conference on Machine Learning (ICML), 2012.
19. Ross, S., Gordon, G., and Bagnell, A. A reduction of imitation learning and structured prediction to no-regret online learning. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2011.
20. Ross, S., Melik-Barkhudarov, N., Shankar, K. Shaurya, Wendel, A., Dey, D., Bagnell, J. A., and Hebert, M. Learning monocular reactive UAV control in cluttered natural environments. In International Conference on Robotics and Automation (ICRA), 2013.
21. Theodorou, E., Buchli, J., and Schaal, S. Reinforcement learning of motor skills in high dimensions: a path integral approach. In International Conference on Robotics and Automation (ICRA), 2010.
22. Todorov, E. Linearly-solvable Markov decision problems. In Advances in Neural Information Processing Systems (NIPS), 2006.
23. Todorov, E. and Li, W. A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems. In American Control Conference (ACC), 2005.
24. Todorov, E., Erez, T., and Tassa, Y. Mu Jo Co: A physics engine for model-based control. In International Conference on Intelligent Robots and Systems (IROS), 2012.
25. Yin, K., Loken, K., and van de Panne, M. SIMBICON: simple biped locomotion control. ACM Transactions Graphics, 26(3), 2007.
26. Ziebart, B. Modeling purposeful adaptive behavior with the principle of maximum causal entropy. PhD thesis, Carnegie Mellon University, 2010.