Transfer learning with Partially Constrained Models: Application to reinforcement learning of linked multicomponent robot system control

Robotics and Autonomous Systems

Volumn 61, Issue 7, 2013, Pages 694-703

  Fernandez Gauna, Borja ^a   Lopez Guede, Jose Manuel ^a   Graña, Manuel ^a  

^a UNIVERSITY OF THE BASQUE COUNTRY UPV EHU   (Spain)

Author keywords

Hose transportation; Linked multicomponent robotic systems; Reinforcement learning; Transfer learning

Indexed keywords

CONSTRAINED SYSTEMS; HIERARCHICAL APPROACH; MARKOV DECISION PROCESSES; PHYSICAL CONSTRAINTS; ROBOTIC SYSTEMS; STATE-VALUE FUNCTIONS; TRANSFER LEARNING; UNDER-CONSTRAINED SYSTEMS;

HOSE; LEARNING ALGORITHMS; MARKOV PROCESSES;

REINFORCEMENT LEARNING;

EID: 84878315635     PISSN: 09218890     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.robot.2012.07.020     Document Type: Article

References (37)

1. R.S. Sutton, and A.G. Barto Reinforcement Learning: An Introduction 1998 MIT Press
2. M. Asada, S. Noda, S. Tawaratsumida, K. Hosoda, Vision-based behavior acquisition for a shooting robot by using a reinforcement learning, in: Proceedings of IAPR/IEEE Workshop on Visual Behaviors-1994, pp. 112-118, 1994.
3. M.J. Mataric Reinforcement learning in the multi-robot domain Autonomous Robots 4 1997 73 83
4. Y. Takahashi, M. Asada, Modular learning systems for soccer robot, in: Proceedings of the Fourth International Symposium on Human and Artificial Intelligence Systems, pp. 370-375, 2004.
5. Z. Kalmar, C. Szepesvari, and A. Lorincz Modular reinforcement learning: an application to a real robot task A. Birk, J. Demiris, Learning Robots LNCS vol. 1545 1998 Springer Berlin Heidelberg 29 45
6. R.J. Duro, M. Graña, and J. de Lope On the potential contributions of hybrid intelligent approaches to multicomponent robotic system development Information Sciences 180 14 2010 2635 2648
7. B. Fernandez-Gauna, J.M. Lopez-Guede, and E. Zulueta Linked multicomponent robotic systems: basic assessment of linking element dynamical effect E. Corchado, M. Graña, A. Savio, Hybrid Artificial Intelligence Systems, Part I, Vol. 6076 2010 Springer Verlag 73 79
8. B. Fernandez-Gauna, J.M. Lopez-Guede, E. Zulueta, and M. Graña Learning hose transport control with Q-learning Neural Network World 20 7 2010 913 923
9. B. Fernandez-Gauna, J.M. Lopez-Guede, M. Graña, Modular q-learning with state-action vetoes for linked multi-component robotic systems, International Journal of Applied Mathematics and Computer Science (2012) (in press).
10. M.E. Taylor, and P. Stone Transfer learning for reinforcement learning domains: a survey Journal of Machine Learning Research 10 1 2009 1633 1685
11. Z. Echegoyen, I. Villaverde, R. Moreno, M. Graña, and A. d'Anjou Linked multi-component mobile robots: modeling, simulation and control Robotics and Autonomous Systems 58 12 2010 1292 1305
12. H. Qin, D. Terzopoulos, D-nurbs: a physics-based framework for geometric design, technical report, Los Alamitos, CA. USA, 1996.
13. A. Theetten, L. Grisoni, C. Andriot, and B. Barsky Geometrically exact dynamic splines Computer-Aided Design 40 1 2008 35 48
14. S.S. Antman Nonlinear Problems of Elasticity 1995 Springer-Verlag
15. M.B. Rubin Cosserat Theories: Shells, Rods and Points 2000 Kluwer
16. C. Watkins, P. Dayan, Technical note: Q-learning, in: Machine Learning, vol. 8, pp. 279-292, 1992.
17. T. Dietterich An overview of maxq hierarchical reinforcement learning Berthe Choueiry, Toby Walsh, Abstraction, Reformulation, and Approximation Lecture Notes in Computer Science vol. 1864 2000 Springer Berlin Heidelberg 26 44
18. B. Hengst, Model approximation for hexq hierarchical reinforcement learning, in: ECML 2004, pp. 144-155, 2004.
19. X. Cheng, J. Shen, H. Liu, and G. Gu Multi-robot cooperation based on hierarchical reinforcement learning Lecture Notes in Computer Science 4489 2007 90 97
20. P. Geibel, and F. Wysotzki Risk-sensitive reinforcement learning applied to control under constraints Journal of Artificial Intelligence Research 24 2005 81 108
21. P. Geibel Reinforcement learning for MDPs with constraints Johannes Fürnkranz, Tobias Scheffer, Myra Spiliopoulou, ECML Lecture Notes in Computer Science vol. 4212 2006 Springer 646 653
22. P. Geibel Reinforcement learning with bounded risk Proceedings of the Eighteenth International Conference on Machine Learning 2001 Morgan Kaufmann 162 169
23. M. Heger, Consideration of risk in reinforcement learning, in: XI. International Machine Learning Conference, 1994.
24. P. Abbeel, A.Y. Ng, Exploration and apprenticeship learning in reinforcement learning, in: Proceedings of 21st International Conference on Machine Learning, ICML, pp. 1-8, 2005.
25. A. Hans, D. Schneegaß, A.M. Schäfer, S. Udluft, Safe exploration for reinforcement learning, in: ESANN, pp. 143-148, 2008.
26. R. Sutton, D. Precup, and S. Singh Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning Artificial Intelligence 112 1999 181 211
27. O.G. Selfridge, R.S. Sutton, and A.G. Barto Training and tracking in robotics Proceedings of the 9th International Joint Conference on Artificial Intelligence - Volume 1 1985 Morgan Kaufmann Publishers Inc. San Francisco, CA, USA 670 672
28. A. Lazaric, M. Restelli, A. Bonarini A., Transfer of samples in batch reinforcement learning, in: Proceedings of the 25th Annual ICML, pp. 544-551, 2008.
29. K. Ferguson, S. Mahadevan, Proto-transfer learning in Markov decision processes using spectral methods, in: ICML Workshop on Transfer Learning, 2006.
30. D. Andre, and S.J. Russell State abstraction for programmable reinforcement learning agents Proceedings of the Eighteenth National Conference on Artificial Intelligence 2002 AAAI Press 119 125
31. M.E. Taylor, P. Stone, Representation transfer for reinforcement learning, in: AAAI 2007 Fall Symposium on Computational Approaches to Representation Change during Learning and Development, 2007.
32. M.E. Taylor, P. Stone, Cross-domain transfer for reinforcement learning, in: Proceedings of the Twenty-Fourth International Conference on Machine Learning, pp. 879-886, 2007.
33. C. Guestrin, D. Koller, C. Gearhart, N. Kanodia, Generalizing plans to new environments in relational MDPs, in: International Joint Conference on Artificial Intelligence, IJCAI-03, pp. 1003-1010, 2003.
34. J. Ramon, K. Driessens, and T. Croonenborghs Transfer learning in reinforcement learning problems through partial policy recycling Proceedings of The 18th European Conf. on Machine Learning 2007 Springer-Verlag
35. Tom Croonenborghs, Kurt Driessens, Maurice Bruynooghe, Learning relational options for inductive transfer in relational reinforcement learning, in: Proceedings of the Seventeenth Conference on Inductive Logic Programming, 2007.
36. N.K. Jong, State abstraction discovery from irrelevant state variables, in: Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, pp. 752-757, 2005.
37. M. Graña, and F.J. Torrealdea Hierarchically structured systems European Journal of Operational Research 25 1986 20 26