Article ID: | iaor2009630 |
Country: | Poland |
Volume: | 29 |
Issue: | 4 |
Start Page Number: | 989 |
End Page Number: | 996 |
Publication Date: | Jan 2000 |
Journal: | Control and Cybernetics |
Authors: | Michalski A. |
Keywords: | artificial intelligence, decision: rules, learning |
In this paper an application of decision rules to function representation in reinforcement learning is described. Rules are generated incrementally by method based on rough set theory from instances recorded in state-action-Q-value memory. Simulation experiment investigating the performance of the system and results achieved are reported.