A convergent reinforcement learning algorithm in the continuous case based on a finite difference method

IJCAI International Joint Conference on Artificial Intelligence

Volumn 2, Issue , 1997, Pages 826-831

  Munos, Remi ^a  

^a Cemagref   (France)

Author keywords

[No Author keywords available]

Indexed keywords

CONTINUOUS PROBLEMS; CONTINUOUS PROCESS; CONTINUOUS VARIABLES; FINITE DIFFERENCE APPROXIMATIONS; HAMILTON JACOBI BELLMAN EQUATION; NUMERICAL SCHEME; OPTIMAL CONTROL PROBLEM; OPTIMAL CONTROLS;

ARTIFICIAL INTELLIGENCE; FINITE DIFFERENCE METHOD; LEARNING ALGORITHMS; OPTIMAL CONTROL SYSTEMS; TABLE LOOKUP;

REINFORCEMENT LEARNING;

EID: 0039225090     PISSN: 10450823     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. Marianne Akian. Methodes multigrilles en controle stochastique. PhD thesis, University Paris IX Dauphine, 1990.
2. Leeraon Baird. Residual algorithms : Reinforcement learning with function approximation. Machine Learning : proceedings of the Twelfth International Conference, 1995.
3. Guy Barles and B. Perthame. Comparison principle for dirichlet-type hamilton-jacobi equations and singular perturbations of degenerated elliptic equations. Applied Mathematics and Optimization, 21:21-44, 1990.
4. Guy Barles and P.E. Souganidis. Convergence of approximation schemes for fully nonlinear second order equations. Asymptotic Analysis, 4:271-283, 1991.
5. Guy Barles. Solutions de viscosite des equations de Hamilton-jacobi, volume 17 of Mathe matiques et Applications. Springer-Verlag, 1994.
6. Dimitri P. Bertsekas. Dynamic Programming : Deterministic and Stochastic Models. Prentice Hall, 1987.
7. J.A. Boyan and A.W. Moore. Generalization in reinforcement learning : Safely approximating the value function. Advances in Neural Information Processing Systems, 7, 1995.
8. M.G. Crandall, Hitoshi Ishii, and P.L. Lions. User's guide to viscosity solutions of second order partial differential equations. Bulletin of the American Mathematical Society, 27(1), 1992.
9. Wendell H. Fleming and H. Mete Soner. Controlled Markov Processes and Viscosity Solutions. Applications of Mathematics. Springer-Verlag, 1993.
10. G. Gordon. Stable function approximation in dynamic programming. International Conference on Machine Learning, 1995.
11. Andrew W. Moore. The parti-game algorithm for variable resolution reinforcement learning in multidimensional state space. Advances in Neural Information Processing Systems, 6, 1994.
12. Remi Munos. A convergent reinforcement learning algorithm in the continuous case : the finite-element reinforcement learning. International Conference on Machine Learning, 1996.
13. Christopher J.C.H. Watkins. Learning from delayed reward. PhD thesis, Cambridge University, 1989.