Learning Rates : Evolution versus Temporal Difference Learning

Abstract

Evidently, any learning algorithm can only learn on the basis of the information given to it. This paper presents an initial attempt to place an upper bound on the information rates attainable with standard co-evolution and with TDL. The upper bound for TDL is shown to be much higher than for evolution. To test how well these bounds correlate with actual… (More)

1 Figure or Table

Topics

  • Presentations referencing similar topics