Conditions for the convergence of one-layer networks under reinforcement learning

TitleConditions for the convergence of one-layer networks under reinforcement learning
Publication TypeConference Paper
Year of Publication1990
AuthorsIp, J. C. C., M. R. Ito, and P. D. Lawrence
Conference NameNeural Networks, 1990., 1990 IJCNN International Joint Conference on
Pagination245 -252 vol.2
Date Publishedjun.
Keywordsarbitrarily large one-layer network, convergence, convergence theorem, learning systems, multilayer networks, neural nets, reinforcement learning, single-neuron theorem, theorem proving, training input set

An extension to the convergence theorem for single neurons learning under the AR-P algorithm is proved. The extension shows that if the conditions of the single-neuron theorem are satisfied and if the environment satisfies one of two sufficient conditions, the weights in an arbitrarily large one-layer network will converge with probability one to values with which the network correctly classifies the training input set. One condition requires that for all output vectors, the probability of reinforcement being one (success) has one of two values: the output vectors having at least lk correct elements have the higher probability, whereas the output vectors having less than lk correct elements have the lower probability. The alternative condition requires that the reinforcement have a higher probability of being one for output vectors having a higher number of correct elements. The extension and its proof are significant because they further the understanding of the factors affecting the convergence of multilayer networks under reinforcement learning


a place of mind, The University of British Columbia

Electrical and Computer Engineering
2332 Main Mall
Vancouver, BC Canada V6T 1Z4
Tel +1.604.822.2872
Fax +1.604.822.5949

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2020 The University of British Columbia