Search Results for author: Ronald J. Williams

Found 2 papers, 2 papers with code

Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

1 code implementation Machine Learning 1992 Ronald J. Williams

This article presents a general class of associative reinforcement learning algorithms for connectionist networks containing stochastic units.

reinforcement-learning

Learning Internal Representations by Error Propagation

1 code implementation20 Feb 1986 David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams

The rule, called the generalized delta rule, is a simple scheme for implementing a gradient descent method for finding weights that minimize the sum squared error of the system's performance.

Cannot find the paper you are looking for? You can Submit a new open access paper.