The definitions above, separated by ten years, represent two very different conceptions of learning. For Simon learning depends on an internal change in representation, and for Kaelbling it is instead measured in terms of an external change in behaviour. Furthermore, Kaelbling's focus on the situatedness of the learning system being embedded in its environment reflects the recent experience gained by much direct experimentation with physical robots.
Hexmoor H and Meeden L, eds, 1996. ROBOLEARN 96: An International Workshop on Learning for Autonomous Agents SUNY at Buffalo, Technical Report 96−11, Computer Science, Buffalo, NY. (Information about the workshop and related discussions can be obtained at: http://www.cs.buffalo.edu/-hexmoor/ robolearn96.html.)
Simon H, 1983. “Why should machines learn?” In Carbonell J, Michalski R and Mitchell T, eds, Machine Learning: An Artificia1 Intelligence Approach. Tioga Press, CA.
Abstract: The definitions above, separated by ten years, represent two very different conceptions of learning. For Simon learning depends on an internal change in representation, and for Kaelbling it is instead measured in terms of an external change in behaviour. Furthermore, Kaelbling's focus on the situatedness of the learning system being embedded in its environment reflects the recent experience gained by much direct experimentation with physical robots.
