25,161
edits
Changes
no edit summary
[[FILE:gotemporaldiffeval.jpg|none|border|text-bottom|543px|link=http://nic.schraudolph.org/bib2html/b2hd-SchDaySej94.html]]
A modular network architecture that takes advantage of board symmetries,<br/>
translation invariance and localized reinforcement to evaluate Go positions <ref>Image 1 from [[Nicol N. Schraudolph]], [[Peter Dayan]], [[Terrence J. Sejnowski]] ('''19941993'''). ''[https://nicpapers.schraudolphnips.orgcc/bib2htmlpaper/b2hd820-temporal-difference-learning-of-position-SchDaySej94.html evaluation-in-the-game-of-go Temporal Difference Learning of Position Evaluation in the Game of Go]''. [httphttps://papers.nips.cc/book/advances-in-neural-information-processing-systems-6-1993 Advances in Neural Information Processing Systems 6NIPS 1993]</ref>
=Selected Publications=
