Adaptive choice of grid and time in reinforcement learning

Advances in Neural Information Processing Systems

Volumn , Issue , 1998, Pages 1036-1042

  Pareigis, Stephan ^a  

^a UNIVERSITY OF KIEL   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

OPTIMIZATION;

CONTINUOUS STATE; DETERMINISTIC SYSTEMS; GRID REFINEMENT; INFINITE HORIZON DISCOUNTED COSTS; LEARNING RATES; LOCAL ERROR ESTIMATE; OPTIMAL VALUE FUNCTIONS; SPACE DISCRETIZATIONS;

REINFORCEMENT LEARNING;

EID: 0039225087     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. E. Bänsch. Local mesh refinement in 2 and 3 dimensions. IMPACT Comput. Set. Engrg. 3, Vol 3:181-191, 1991.
2. M. Falcone. A numerical approach to the infinite horizon problem of deterministic control theory. Appl Math Optim 15:1-13, 1987.
3. R. Gonzalez and M. Tidball. On the rates of convergence of fully discrete solutions of Hamilton-Jacobi equations. INRIA, Rapports de Recherche, No 1376, Programme 5, 1991.
4. L. Grüne. An adaptive grid scheme for the discrete Ilamilton-Jacobi-Bellrrian equation. Numerische Mathematik, Vol 75, No. 3:319-337, 1997.
5. A. W. Moore and C. G. Atkeson. The parti-garrie algorithm for variable resolution reinforcement learning in multidimensional state-spaces. Machine Learning, Volume 21, 1995.
6. S. Pareigis. Lernen der Losung der Bellman-Gleichung durch Beohachtung von kontinuierlichen Prozefien. PhD thesis, Universitat Kiel, 1996.
7. S. Pareigis. Multi-grid methods for reinforcement learning in controlled diffusion processes. In D. S. Touretzky, M. C. Mozer, and M. E. Hasselmo, editors, Advances in Neural Information Processing Systems, volume 9. The MIT Press, Cambridge, 1997.