Reinforcement learning acceleration through autonomous subgoal discovery

Proceedings of the 2005 International Conference on Machine Learning; Models, Technologies and Applications, MLMTA'05

Volumn , Issue , 2005, Pages 69-74

  Asadi, Mehran ^a   Huber, Manfred ^a  

^a University of Texas at Arlington   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ACTION SPACES; HIERARCHICAL STATE; LEARNING TIME; REINFORCEMENT LEARNING AGENTS; STATE SPACES; SUBGOALS; TIME SPENT;

REINFORCEMENT; REINFORCEMENT LEARNING; ROBOT LEARNING;

EDUCATION;

EID: 60749083025     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. R. Parr, "Hierarchical control and learning for markov decision processes," Ph.D. dissertation, University of California, Berkeley, CA, 1998.
2. T. G. Dietterich, "An overview of maxq hierarchical reinforcement learning," Lecture Notes in Computer Science, vol. 1864, 2000.
3. B. Digney, "Emergent hierarchical control structures: Learning reactive / hierarchical relationships in reinforcement environments," in Proceedings of the Fourth Conference on the Simulation of Adaptive Behavior, 1996.
4. M. Asadi and M. Huber, "State space reduction for hierarchical reinforcement learning," in In Proceedings of the 17th International FLAIRS Conference. AAAI, 2004, pp. 509-514.
5. S. Goel and M. Huber, "Subgoal discovery for hierarchical reinforcement learning using learned policies," in In Proceedings of the 16th International FLAIRS Conference. AAAI, 2003, pp. 346-350.
6. R. Givan, S. Leach, and T. Dean, "Bounded-parameter markov decision processes," Artificial Intelligence, vol. 122, no. 1-2, pp. 71-109, 2000.
7. C. Boutilier, T. Dean, and S. Hanks, "Decision-theoretic planning: Structural assumptions and computational leverage," Journal of Artificial Intelligence Research, vol. 11, pp. 1-94, 1999.
8. R. Sutton, D. Precup, and S. Singh, "Between MDPs and Semi-MDPs: Learning, planning, and representing knowledge at multiple temporal scales," Artificial Intelligence, vol. 112, pp. 181-211, 1999.
9. K. Kim and T. Dean, "Solving factored MDPs using non-homogeneous partitions," Artificial Intelligence, vol. 147, pp. 225-251, 2003.
10. T. Dean, R. Givan, and M. Greig, "Equivalence notions and model minimization in markov decision processes," in Special issue on planning with uncertainty and incomplete information, 2003, pp. 163-223.