Basis function construction for hierarchical reinforcement learning

Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS

Volumn 2, Issue , 2010, Pages 747-754

  Osentoski, Sarah ^a   Mahadevan, Sridhar ^b  

^a Brown Univerity   (United States)

^b University of Massachusetts Amherst   (United States)

Author keywords

Hierarchical Reinforcement Learning; Representation Discovery; Semi Markov Decision Processes

Indexed keywords

AUTONOMOUS AGENTS; FUNCTIONS; MARKOV PROCESSES; MULTI AGENT SYSTEMS; SPECTRUM ANALYSIS; TELECOMMUNICATION NETWORKS;

APPROXIMATION ARCHITECTURE; FUNCTION APPROXIMATION; HIERARCHICAL REINFORCEMENT LEARNING; MARKOV DECISION PROCESSES; PARAMETER ESTIMATION METHOD; REPRESENTATION DISCOVERY; SEMI-MARKOV DECISION PROCESS; TEMPORAL ABSTRACTION;

REINFORCEMENT LEARNING;

EID: 84899441331     PISSN: 15488403     EISSN: 15582914     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. A. Barto and S. Mahadevan. Recent advances in hierarchical reinforcement learning. Special Issue on Reinforcement Learning, Discrete Event Systems Jouranl, 13:41-77, 2003.
2. F. Chung. Spectral Graph Theory. Number 92 in CBMS Regional Conference Series in Mathematics. American Mathematical Society, 1997.
3. F. Chung. Laplacians and the Cheeger inequality for directed graphs. Annals of Combinatorics, 9:1-19, 2005.
4. T. Dietterich. The MAXQ method for hierarchical reinforcement learning. In Proceedings of the Fifteenth International Conference on Machine Learning, pages 118-126. Morgan Kaufman, 1998.
5. T. Dietterich. Hierarchical reinforcemnt learning with the MAXQ value function decomposition. Journal of Artificial Intelligence Research, 13:277-303, 2000.
6. M. Ghavamzadeh and S. Mahadevan. Hierarchical average-reward reinforcement learning. Journal of Machine Learning Research, 8:2629-2669, 2007.
7. P. W. Keller, S. Mannor, and D. Precup. Automatic basis function construction for approximate dynamic programming and reinforcement learning. In Proceedings of the 23rd International Conference on Machine Learning, New York, NY, 2006. ACM Press.
8. S. Mahadevan. Proto-Value Functions: Developmental Reinforcement Learning. In Proceedings of the 22nd International Conference on Machine Learning, pages 553-560, New York, NY, 2005. ACM Press.
9. S. Osentoski and S. Mahadevan. Learning state-action basis functions for hierarchical MDPs. In Proceedings of the 24th International Conference on Machine Learning, 2007.
10. R. Parr, C. Painter-Wakefield, L. Li, and M. Littman. Analyzing feature generation for value-function approximation. In Proceedings of the International Conference on Machine Learning (ICML), 2007.
11. R. Parr and S. Russell. Reinforcement learning with hierarchies of machines. In Advances in Neural Information Processing Systems 10, pages 1043-1049. MIT Press, 1998.
12. M. Petrik. An analysis of Laplacian methods for value function approximation in MDPs. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2007.
13. R. Sutton, D. Precup, and S. Singh. Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence, 112:181-211, 1999.
14. C. K. I. Williams and M. Seeger. Using the Nyström method to speed up kernel machines. In Advances in Neural Information Processing Systems 13, 2001. 54