Task similarity measures for transfer in reinforcement learning task libraries

Proceedings of the International Joint Conference on Neural Networks

Volumn 2, Issue , 2005, Pages 803-808

  Carroll, James L ^a   Seppi, Kevin ^a  

^a 3361 TMCB   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

POLICY OVERLAP; REINFORCEMENT LEARNING; TASK LIBRARIES; TRANSFER TIME;

COMPUTER SIMULATION; DATA TRANSFER; DIGITAL LIBRARIES;

LEARNING SYSTEMS;

EID: 33745957999     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/IJCNN.2005.1555955     Document Type: Conference Paper

References (10)

1. T. Peterson, N. Owens, and J. L. Carroll, "Automated shaping as applied to robot navigation," in IEEE International Conference on Robotics and Automation, Korea, 2001. [Online]. Available: http://james.jlcarroll.net/ publications/shaping.pdf
2. J. L. Carroll, T. Peterson, and K. Seppi, "Reinforcement learning task clustering (rltc)," in ICMLA, LA California USA, 2003. [Online]. Available: http://james.jlcarroll. net/publications/rltc.pdf
3. J. L. Carroll, T. Peterson, and N. Owens, "Memory-guided exploration in reinforcement learning," in IJCNN2001, Washington, D.C., 2001. [Online]. Available: http://james.jlcarroll.net/publications/mge9.pdf
4. M. Bowling and M. Veloso, "Reusing learned policies between similar problems," in Proceedings of the AI*AI-98 Workshop on New Trends in Robotics, Padua, Italy, October 1998.
5. A. Robins, "Transfer in cognition," in Learning to Learn, L. P. Sebastian Thrun, Ed. San Franciso, Ca.: Morgan Kaufmann, 1998, ch. 3, pp. 45-67.
6. J. Randlov and P. Alstrom, "Learning to drive a bicycle using reinforcement learnnig and shaping," in Machine Learning: Proceeding of the Eleventh International Conference. Morgan Kaufmann, CA, 1999.
7. J. L. Carroll, "Task localization, clustering, and transfer: towards a reinforcement learnign task library system," Master's thesis, Brigham Young University, 2005.
8. S. Thrun and A. Schwartz, "Finding structure in reinforcement learning," in Advances in Neural Information Processing Systems 7, G. Tesauro, D. Touretzky, and T. Leen, Eds., 1995, pp. 385-392.
9. S. Thrun and J. O'Sullivan, "Clustering learning tasks and the selective cross-task transfer of knowledge," 1995. [Online]. Available: citeseer.nj.nec.com/thrun95clustering.html
10. _, "Discovering structure in multiple learning tasks: The TC algorithm," in International Conference on Machine Learning,1996, pp. 489-497. [Online]. Available: citeseer.nj.nec.com/thrun96discovering.html