The book learning feature in LearningLemming is not applied during the game. Instead, parts of the game to learn from are saved to a file, and then a separate learning program does a post-mortem analysis and saves off conclusions for LearningLemming to use in future games. The other type of learning Sam played with in LearningLemming is parameter tuning, and a rough form of this is used in the Hannibal development process [2].
a private, experimental and Chess Engine Communication Protocol compliant chess engine [1] by Sam Hamilton with focus on Learning techniques, and along with Edsel Apostol's Twisted Logic, ancestor of Hannibal.
The book learning feature in LearningLemming is not applied during the game. Instead, parts of the game to learn from are saved to a file, and then a separate learning program does a post-mortem analysis and saves off conclusions for LearningLemming to use in future games. The other type of learning Sam played with in LearningLemming is parameter tuning, and a rough form of this is used in the Hannibal development process [2].
Table of Contents
Tournament Play
In the 2006-2009 timeframe, LearningLemming played three ACCA Americas' Computer Chess Championship, the ACCA 2006, the ACCA 2007 (third place, even leading after four rounds [4]), and the ACCA 2008, further two ACCA World Computer Rapid Chess Championship, the WCRCC 2007 and WCRCC 2009, and two CCT Tournaments, CCT9 and CCT10.Selected Games
WCRCC 2009, round 12, LearningLemming - Rybka [5]See also
Forum Posts
External Links
References
What links here?
Up one level