## Optimal reinforcements of generalized learning processesKyushu University, Research Institute of Fundamental Information Science, 1978 - Education - 10 pages |

### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Common terms and phrases

absorbing process arbitrary assumption bility CHICAGO compact set correct response probability define denote deterministic stationary reinforcement discount exists an optimal expected average fi(ir)n finite Five linear operator following conclusion formulated as follows function Fundamental Information Science given giving an outcome initial distribution Institute of Fundamental Japan KYUSHU UNIVERSITY learning models learning processes LIBRARY linear operator model Markovian decision processes maximize the correct ment model is determined n-th Norman's linear models Norman's models optimal deterministic stationary Optimal Reinforcements Pr(J Pr(k present paper proba probability measure probability space random variable reinforcement tt Research Institute sample Seigo set of outcomes shows the following stimulus elements conditioned sufficient condition theorem transformation transition law v(Cn values x e X