The Rescorla-Wagner Algorithm and Maximum Likelihood Estimation of Causal Parameters
Abstract
This paper analyzes generalization of the classic Rescorla-Wagner (R- W) learning algorithm and studies their relationship to Maximum Like- lihood estimation of causal parameters. We prove that the parameters of two popular causal models, P and P C, can be learnt by the same generalized linear Rescorla-Wagner (GLRW) algorithm provided gener- icity conditions apply. We characterize the fixed points of these GLRW algorithms and calculate the fluctuations about them, assuming that the input is a set of i.i.d. samples from a fixed (unknown) distribution. We describe how to determine convergence conditions and calculate conver- gence rates for the GLRW algorithms under these conditions.
Cite
Text
Yuille. "The Rescorla-Wagner Algorithm and Maximum Likelihood Estimation of Causal Parameters." Neural Information Processing Systems, 2004.Markdown
[Yuille. "The Rescorla-Wagner Algorithm and Maximum Likelihood Estimation of Causal Parameters." Neural Information Processing Systems, 2004.](https://mlanthology.org/neurips/2004/yuille2004neurips-rescorlawagner/)BibTeX
@inproceedings{yuille2004neurips-rescorlawagner,
title = {{The Rescorla-Wagner Algorithm and Maximum Likelihood Estimation of Causal Parameters}},
author = {Yuille, Alan L.},
booktitle = {Neural Information Processing Systems},
year = {2004},
pages = {1585-1592},
url = {https://mlanthology.org/neurips/2004/yuille2004neurips-rescorlawagner/}
}