From 85516b8cc8a6c5767ab29917556f5b30b4482b73 Mon Sep 17 00:00:00 2001 From: Terrence Brannon Date: Fri, 7 Dec 2018 22:02:54 +0000 Subject: [PATCH] Minor copyedits in landmark.el * lisp/obsolete/landmark.el: Fix author's email and commentary. --- lisp/obsolete/landmark.el | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/lisp/obsolete/landmark.el b/lisp/obsolete/landmark.el index effea95cd8f..c4c4c7a20f6 100644 --- a/lisp/obsolete/landmark.el +++ b/lisp/obsolete/landmark.el @@ -2,7 +2,7 @@ ;; Copyright (C) 1996-1997, 2000-2018 Free Software Foundation, Inc. -;; Author: Terrence Brannon (was: ) +;; Author: Terrence Brannon ;; Created: December 16, 1996 - first release to usenet ;; Keywords: games, neural network, adaptive search, chemotaxis ;; Version: 1.0 @@ -36,7 +36,7 @@ ;; the smell of the tree increases, then the weights in the robot's ;; brain are adjusted to encourage this odor-driven behavior in the ;; future. If the smell of the tree decreases, the robots weights are -;; adjusted to discourage a correct move. +;; adjusted to discourage that odor-driven behavior. ;; In laymen's terms, the search space is initially flat. The point ;; of training is to "turn up the edges of the search space" so that @@ -53,6 +53,13 @@ ;; a single move, one moves east,west and south, then both east and ;; west will be improved when they shouldn't +;; The source code was developed as part of a course on Brain Theory +;; and Neural Networks at the University of Southern California. The +;; original problem description and solution appeared in 1981 in the +;; paper "Landmark Learning: An Illustration of Associative +;; Search" authored by Andrew G. Barto and Richard S. Sutton and +;; published to Biological Cybernetics. + ;; Many thanks to Yuri Pryadkin for this ;; concise problem description.