Henk Mannen 1
Henk Mannen,
a Dutch computer scientist, chess player 1, and sales and human resource manager. He holds a Master's degree from Utrecht University in 2003, where he worked with Marco Wiering on reinforcement learning and temporal difference learning in chess. In their experiments, they used Tom Kerrigan's TSCP 1.811, and trained several different chess evaluation functions (neural networks) by using TD(λ) learning on a set of database games 2. __FORCETOC__
Publications
- Henk Mannen (2003). Learning to play chess using reinforcement learning with database games. Master’s thesis, Cognitive Artificial Intelligence, Utrecht University, pdf
- Henk Mannen, Marco Wiering (2004). Learning to play chess using TD(λ)-learning with database games. Cognitive Artificial Intelligence, Utrecht University, Benelearn’04, pdf
- Marco Wiering, Jan Peter Patist, Henk Mannen (2005). Learning to Play Board Games using Temporal Difference Methods. Technical Report, Utrecht University, UU-CS-2005-048, pdf
External Links
References
Henk Mannen, Marco Wiering (2004). Learning to play chess using TD(λ)-learning with database games. Cognitive Artificial Intelligence, Utrecht University, Benelearn’04↩︎