Title :
Knowledge extraction from reinforcement learning
Author_Institution :
NEC Res. Inst., Princeton, NJ, USA
Abstract :
This paper deals with knowledge extraction from reinforcement learners. It addresses two approaches towards knowledge extraction: the extraction of explicit, symbolic rules front neural reinforcement learners; and the extraction of complete plans from such learners. The advantages of such knowledge extraction include: the improvement of learning (especially with the rule extraction approach); and the improvement of the usability of results of learning
Keywords :
knowledge acquisition; learning (artificial intelligence); neural nets; symbol manipulation; knowledge extraction; neural networks; reinforcement learning; rule extraction; symbolic rules; Boltzmann distribution; Collaborative work; Decision making; Learning; National electric code; Neural networks; Stochastic processes; Sun; Usability;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.833476
