Discovering options from example trajectories

Proceedings of the 26th International Conference On Machine Learning, ICML 2009

Volumn , Issue , 2009, Pages 1217-1224

  Zang, Peng ^a   Zhou, Peng ^a   Minnen, David ^a   Isbell, Charles ^a  

^a Georgia Institute of Technology   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DIFFERENT DOMAINS; LEARNING PROCESS; NOVEL TECHNIQUES; OPTIMAL TRAJECTORIES; PROBLEM DECOMPOSITION;

REINFORCEMENT; ROBOT LEARNING;

EDUCATION;

EID: 71149102986     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. Dietterich, T. G. (1998). The MAXQ method for hierarchical reinforcement learning. Intl. Conf. on Machine Learning (pp. 118-126).
2. Hengst, B. (2002). Discovering hierarchy in reinforcement learning with hexq. Intl. Conf. on Machine Learning (pp. 243-250).
3. Jonsson, A., & Barto, A. (2006). Causal graph based decomposition of factored mdps. Journal of Machine Learning Research, 7, 2259-2301.
4. Mannor, S., Menache, I., Hoze, A., & Klein, U. (2004). Dynamic abstraction in reinforcement learning via clustering. Intl. Conf. on Machine Learning (pp. 560-567).
5. McGovern, A., & Barto, A. G. (2001). Automatic discovery of subgoals in reinforcement learning using diverse density. Intl. Conf on Machine Learning (pp. 361-368).
6. Mehta, N., Ray, S., Tadepalli, P., & Dietterich, T. (2008). Automatic discovery and transfer of maxq hierarchies. Intl. Conf. on Machine Learning (pp. 648-655).
7. Parr, R., & Russell, S. (1997). Reinforcement learning with hierarchies of machines. Advances in Neural Information Processing Systems (pp. 1043-1049).
8. Pickett, M., & Barto, A. G. (2002). Policyblocks: An algorithm for creating useful macro-actions in reinforcement learning. Intl. Conf. on Machine Learning (pp. 506-513).
9. Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: An introduction. Cambridge, MA: MIT Press.
10. Sutton, R. S., Precup, D., & Singh, S. P. (1999). Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence, 112, 181-211.
11. Ukkonen., E. (1992). Constructing suffix-trees on-line in linear time. Algorithms, 1, 484-492.