Algebraic results and bottom-up algorithm for policies generalization in reinforcement learning using concept lattices

Nonlinear Analysis: Hybrid Systems

Volumn 2, Issue 2, 2008, Pages 684-694

  Ricordeau, Marc ^a   Liquière, Michel ^a  

^a LIRMM   (France)

Author keywords

Galois lattices; Reinforcement learning

Indexed keywords

EID: 41249094659     PISSN: 1751570X     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.nahs.2006.12.001     Document Type: Article

References (16)

1. Watkins C., and Dayan P. Q-learning. Machine Learning 8 (1992) 279-292
2. Sutton R.S., Precup D., and Singh S. Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence 112 1-2 (1999) 181-211
3. M.R. James, S. Singh, Learning and discovery of predictive state representations in dynamical systems with reset, in: ICML 2004, Dpt of Computer Science and Engineering, University of Michigan, Ann Arbor, 2004, pp. 417-424
4. R. Munos, Error bounds for approximate policy iteration, in: International Conference on Machine Learning ICML 2003, Centre de Mathématiques Appliquées, Ecole Polytechnique, Palaiseau, France, 2003, pp. 560-567
5. A. McCallum, Reinforcement learning with selective perception and hidden state, Ph.D. Thesis, 1996
6. B. Ravindran, A.G. Barto, SMDP homomorphisms: An algebraic approach to abstraction in semi Markov decision processes, in: IJCAI 2003, AAAI Press edition, Dpt of Computer Science, University of Massachussetts, Amherst, 2003, pp. 1011-1016
7. Givan R., Dean T., and Greig M. Equivalence notions and model minimization in Markov decision processes. Artificial Intelligence 147 1-2 (2003) 163-223
8. Dietterich T.G. State abstraction in maxq hierachical reinforcement learning. Artificial Intelligence Research 13 (2000) 227-303
9. Dzeroski S., Raedt L.D., and Driessens K. Relational reinforcement learning. Machine Learning 43 (2001) 7-52
10. M. Ricordeau, Q-concept-learning: Generalization with concept lattice representation in reinforcement learning, in: I.C. Society (Ed.), International Conference on Tools with Artificial Intelligence, ICTAI 03, Lirmm, Montpellier, 2003, pp. 316-323
11. Sutton R.S., and Barto A.G. Reinforcement Learning: An Introduction (1998), MIT Press
12. Ganter B., and Wille R. Formal Concept Analysis: Mathematical Foundations (1999), Springer
13. Mitchell T.M. Machine Learning (1997), McGraw-Hill
14. M. Liquière, J. Sallantin, Structural machine learning with Galois lattice and graphs, in: M.K. Ed (Ed.), ICML 1998, Lirmm, Montpellier, Morgan Kaufmann Ed, 1998, pp. 305-313
15. R. Munos, Finite-element methods with local triangulation refinement for continuous reinforcement learning problems, 1997
16. A. McCallum, Efficiently inducing features of conditional random fields, in: Conference on Uncertainty in Articifical Intelligence, UAI, 2003, Dpt of Computer Science, University of Massachussetts, Amherst, 2003