A physics-based model prior for object-oriented MDPs

31st International Conference on Machine Learning, ICML 2014

Volumn 4, Issue , 2014, Pages 2788-2796

  Scholz, Jonathan ^a   Levihn, Martin ^a   Isbell, Charles L ^a   Wingate, David ^b  

^a GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

^b MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; REINFORCEMENT LEARNING;

INDUCTIVE BIAS; MULTI-OBJECT DYNAMICS; NATURAL WORLD; OBJECT ORIENTED; PHYSICAL DYNAMICS; PHYSICAL ENVIRONMENTS; PHYSICS-BASED MODELING; RELATIONAL REPRESENTATIONS;

ROBOTICS;

EID: 84919788574     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (23)

1. Atkeson, C., An, C., and Hollerbach, J. Estimation of inertial parameters of manipulator loads and links. The International Journal of Robotics Research, 5(3), 1986.
2. Bhat, K., Seitz, S., Popovic, J., and Khosla, P. Computing the physical parameters of rigid-body motion from video. ECCV, 2002.
3. Bhat, K.S., Twigg, C.D., Hodgins, J.K., Khosla, P.K., Popovic, Z., and Seitz, S.M. Estimating cloth simulation parameters from video. In SIGGRAPH. Eurographics Association, 2003.
4. Catto, Erin. Box2D physics engine, 2013. URL http://www.box2d.org.
5. Degris, T., Sigaud, O., and Wuillemin, P. Learning the structure of factored markov decision processes in reinforcement learning problems. In ICML. ACM, 2006.
6. Deisenroth, M., Rasmussen, C., and Fox, D. Learning to control a low-cost manipulator using data-efficient reinforcement learning. 2011.
7. Deisenroth, M., Neumann, G., and Peters, J. A survey on policy search for robotics. Foundations and Trends in Robotics, 2013.
8. Diuk, C., Cohen, A., and Littman, M.L. An object-oriented representation for efficient reinforcement learning. In ICML. ACM, 2008.
9. Duff, D.J., Wyatt, J., and Stolkin, R. Motion estimation using physical simulation. In ICRA. IEEE, 2010.
10. Kakadiaris, L. and Metaxas, D. Model-based estimation of 3d human motion. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 22(12), 2000.
11. Landau, loan Dore. Adaptive control: Algorithms, analysis and applications. Springer, 2011.
12. LaValle, S. Rapidly-exploring random trees a new tool for path planning. 1998.
13. LaValle, S. Planning algorithms. Cambridge university press, 2006.
14. Leffler, Bethany R, Littman, Michael L, and Edmunds, Timothy. Efficient reinforcement learning with relocatable action models. In Proceedings of AAAI, volume 22. Menlo Park, CA; Cambridge, MA; London; AAAI Press; MIT Press; 1999, 2007.
15. Levihn, M., Scholz, J., and Stilman, M. Hierarchical decision theoretic planning for navigation among movable obstacles. In WAFR, 2012.
16. Levihn, M., Scholz, J., and Stilman, M. Planning with movable obstacles in continuous environments with uncertain dynamics. In ICRA, May 2013.
17. Liu, C.K. Dart: Dynamic animation and robotics toolkit, 2013. URL https://github.com/dartsim/dart/wiki.
18. Liu, C.K., Hertzmann, A., and Popovic, Z. Learning physics-based motion style with nonlinear inverse optimization. In ACM Transactions on Graphics (TOG), volume 24. ACM, 2005.
19. Nguyen-Tuong, D. and Peters, J. Model learning for robot control: A survey. Cognitive processing, 12(4), 2011.
20. Niebergall, M and Hahn, H. Identification of the ten inertia parameters of a rigid body. Nonlinear Dynamics, 13(4), 1997.
21. Sontag, E. Mathematical control theory: deterministic finite dimensional systems, volume 6. Springer, 1998.
22. Stam, J. Stable fluids. In Proceedings of the 26th annual conference on Computer graphics and interactive techniques. ACM Press/Addison-Wesley Publishing Co., 1999.
23. Vlassis, N., Ghavamzadeh, M., Mannor, S., and Poupart, P. Bayesian reinforcement learning. In Reinforcement Learning. Springer, 2012.