Comparison of CMACs and radial basis functions for local function approximators in reinforcement learning

IEEE International Conference on Neural Networks - Conference Proceedings

Volumn 2, Issue , 1997, Pages 834-837

  Kretchmar, R M ^a   Anderson, C W ^a  

^a Colorado State University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

LOCAL CHARACTERISTICS; LOCAL FUNCTIONS; LOCAL GENERALIZATION; Q-LEARNING; RADIAL BASIS FUNCTIONS; RESEARCH EFFORTS; VALUE FUNCTION APPROXIMATION;

NEURAL NETWORKS; RADIAL BASIS FUNCTION NETWORKS; APPROXIMATION THEORY; CONTROL THEORY; FUNCTIONS; STATE SPACE METHODS;

REINFORCEMENT LEARNING; LEARNING SYSTEMS;

CEREBELLAR MODEL ARTICULATION CONTROLLER (CMAC); LOCAL FUNCTION APPROXIMATORS; RADIAL BASIS FUNCTIONS; REINFORCEMENT LEARNING;

EID: 0030721089     PISSN: 10987576     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICNN.1997.616132     Document Type: Conference Paper

References (7)

1. Anderson, C. (1993) Q-Learning with Hidden-Unit Restarting. Advances in Neural Information Processing Systems, volume 5, S. J. Hanson, J. D. Cowan, and C. L. Giles, eds., Morgan Kaufmann Publishers, San Mateo, CA, pp. 81-88.
2. Miller, W. T., F. H. Glanz, and L. G. Kraft. (1990). CMAC: An associative neural network alternative to backpropaga-tion. Proceedings of IEEE, 78, pp. 1561-1567.
3. Molina, C. andNiranjan, M. (1996) Pruning with replacement on limited resource allocating networks by f-projections. Neural Computation, vol. 8., no. 4, pp. 855-868.
4. Piatt, J.C. (1991) A resource-allocating network for function interpolation. Neural Computation, 3:213-225.
5. Rittwager, F. (1996) Temporal-difference based self-organization for reinforcement learning with radial basis functions. Masters Thesis, Dept. of Computer Science, Colorado State University.
6. Sutton, R.S. (1996) Generalization in reinforcement learning: Successful examples using sparse coarse coding. In Advances in Neural Information Processing Systems 8, Cambridge, MA: MT Press.
7. Watkins, C. J. (1989) Learning from delayed rewards. Ph.D. Thesis, Cambridge University.