Compositional planning using optimal option models

Proceedings of the 29th International Conference on Machine Learning, ICML 2012

Volumn 2, Issue , 2012, Pages 1063-1070

  Silver, David ^a   Ciosek, Kamil ^a  

^a UNIVERSITY COLLEGE LONDON   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

BELLMAN EQUATIONS; CLASSICAL PLANNING; DYNAMIC PROGRAMMING ALGORITHM; FUNDAMENTAL OPERATIONS; GENERALISATION; LEVELS OF ABSTRACTION; MACRO-OPERATORS; MODEL LEARNING; OPTION MODELS; PRIMITIVE ACTIONS; SUBGOALS; TEMPORAL ABSTRACTION; VALUE FUNCTIONS;

DYNAMIC PROGRAMMING; LEARNING SYSTEMS;

OPTIMIZATION;

EID: 84867135062     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. Amarel, S. On representations of problems of reasoning about actions. Machine Intelligence, 3:131-171, 1968.
2. Andre, D. and Russell, S. State abstraction for programmable reinforcement learning agents. In 18th National Conference on Artificial Intelligence, 2002.
3. Bellman, R. Dynamic Programming. Princeton University Press, 1957.
4. Dietterich, T. Hierarchical reinforcement learning with the MAXQ value function decomposition. Journal of Artificial Intelligence Research, 13:227-303, 2000.
5. Jonsson, A. The role of macros in tractable planning. Journal of Artificial Intelligence Research, 36:471-511, 2009.
6. Konidaris, G. and Barto, A. Efficient skill learning using abstraction selection. In 21st International Joint Conference on Artificial Intelligence, 2009.
7. Korf, R. Learning to solve problems by searching for macrooperators. Pitman Publishing, 1985.
8. Laird, J., Rosenbloom, P., and Newell, A. Chunking in SOAR: The anatomy of a general learning mechanism. Machine Learning, 1(1):1146, 1986.
9. Parr, R. and Russell, S. Reinforcement learning with hierarchies of machines. In Advances in Neural Information Processing Systems 10, 1997.
10. Precup, D., Sutton, R., and Singh, S. Theoretical results on reinforcement learning with temporally abstract options. In 10th European Conference on Machine Learning, 1998.
11. Sacerdoti, E. A structure for plans and behavior. PhD thesis, Stanford University, 1975.
12. Sutton, R. TD models: Modeling the world at a mixture of time scales. In 12th International Conference on Machine Learning, pp. 531-539, 1995.
13. Sutton, R. and Barto, A. Reinforcement Learning: an Introduction. MIT Press, 1998.
14. Sutton, R., Precup, D., and Singh, S. Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence, 112(1-2): 181-211, 1999.