Difference between revisions of "Ryan Hayward"

From Chessprogramming wiki
Jump to: navigation, search
Line 8: Line 8:
 
=Hex Programs=
 
=Hex Programs=
 
After early trials with [https://www.game-ai-forum.org/icga-tournaments/program.php?id=276 Mongoose], the Hex programs [https://www.game-ai-forum.org/icga-tournaments/program.php?id=135 Wolve] ([[13th Computer Olympiad#Hex|2008]]) and [https://www.game-ai-forum.org/icga-tournaments/program.php?id=555 MoHex] ([[14th Computer Olympiad#Hex|2009]], [[15th Computer Olympiad#Hex|2010]], [[16th Computer Olympiad#Hex|2011]], [[17th Computer Olympiad#Hex|2013]], [[18th Computer Olympiad#Hex|2015]] and [[20th Computer Olympiad#Hex|2017]]) won Gold Medals in Hex at the [[Computer Olympiad]].  
 
After early trials with [https://www.game-ai-forum.org/icga-tournaments/program.php?id=276 Mongoose], the Hex programs [https://www.game-ai-forum.org/icga-tournaments/program.php?id=135 Wolve] ([[13th Computer Olympiad#Hex|2008]]) and [https://www.game-ai-forum.org/icga-tournaments/program.php?id=555 MoHex] ([[14th Computer Olympiad#Hex|2009]], [[15th Computer Olympiad#Hex|2010]], [[16th Computer Olympiad#Hex|2011]], [[17th Computer Olympiad#Hex|2013]], [[18th Computer Olympiad#Hex|2015]] and [[20th Computer Olympiad#Hex|2017]]) won Gold Medals in Hex at the [[Computer Olympiad]].  
 
+
<span id="Wolve"></span>
 
==Wolve==
 
==Wolve==
 
Wolve does a truncated [[Alpha-Beta]] search of two and up to four [[Ply|plies]], considering the huge [[Branching Factor]] of Hex.  
 
Wolve does a truncated [[Alpha-Beta]] search of two and up to four [[Ply|plies]], considering the huge [[Branching Factor]] of Hex.  
 
+
<span id="MoHex"></span>
 
==MoHex==
 
==MoHex==
 
Since 2009 [[Monte-Carlo Tree Search]] starts to dominate, and MoHex applies MCTS along with the [[UCT]] framework combined with the allmoves-as-first (AMAF) heuristic to select the best child during tree traversal <ref>[[Broderick Arneson]], [[Ryan Hayward]], [[Philip Henderson]] ('''2010'''). ''Monte Carlo Tree Search in Hex''. [[IEEE#TOCIAIGAMES|IEEE Transactions on Computational Intelligence and AI in Games]], Vol. 2, No. 4, [http://webdocs.cs.ualberta.ca/~hayward/papers/mcts-hex.pdf pdf]</ref>.  
 
Since 2009 [[Monte-Carlo Tree Search]] starts to dominate, and MoHex applies MCTS along with the [[UCT]] framework combined with the allmoves-as-first (AMAF) heuristic to select the best child during tree traversal <ref>[[Broderick Arneson]], [[Ryan Hayward]], [[Philip Henderson]] ('''2010'''). ''Monte Carlo Tree Search in Hex''. [[IEEE#TOCIAIGAMES|IEEE Transactions on Computational Intelligence and AI in Games]], Vol. 2, No. 4, [http://webdocs.cs.ualberta.ca/~hayward/papers/mcts-hex.pdf pdf]</ref>.  
MoHex-CNN, which won the [[20th Computer Olympiad#Hex|13x13 competition of the 20th Computer Olympiad 2017]] is a [[Neural Networks#Convolutional|convolutional neural net]] (CNN) version of MoHex. At each new node of the Monte-Carlo search tree, a policy CNN biases child selection by initializing child visit and win counts with artificial values <ref>* [[Ryan Hayward]], [[Noah Weninger]] ('''2017'''). ''Hex 2017: MoHex wins the 11x11 and 13x13 tournaments''. [[ICGA Journal#39_34|ICGA Journal, Vol. 39, Nos. 3-4]]</ref>.
+
MoHex-CNN, which won the [[20th Computer Olympiad#Hex|13x13 competition of the 20th Computer Olympiad 2017]] is a [[Neural Networks#Convolutional|convolutional neural net]] (CNN) version of MoHex. At each new node of the Monte-Carlo search tree, a policy CNN biases child selection by initializing child visit and win counts with artificial values <ref>[[Ryan Hayward]], [[Noah Weninger]] ('''2017'''). ''Hex 2017: MoHex wins the 11x11 and 13x13 tournaments''. [[ICGA Journal#39_34|ICGA Journal, Vol. 39, Nos. 3-4]]</ref>.
  
 
=Selected Publications=  
 
=Selected Publications=  

Revision as of 21:38, 27 May 2018

Home * People * Ryan Hayward

Ryan B. Hayward [1]

Ryan Bruce Hayward,
a Canadian mathematician, computer scientist, and professor at Department of Computing Science at University of Alberta. Ryan Hayward is particularly interested in Hex, which he learned from Claude Berge. As member of the University of Alberta's GAMES research group [2], he leads a team that developed Hex solver and players.

Hex Programs

After early trials with Mongoose, the Hex programs Wolve (2008) and MoHex (2009, 2010, 2011, 2013, 2015 and 2017) won Gold Medals in Hex at the Computer Olympiad.

Wolve

Wolve does a truncated Alpha-Beta search of two and up to four plies, considering the huge Branching Factor of Hex.

MoHex

Since 2009 Monte-Carlo Tree Search starts to dominate, and MoHex applies MCTS along with the UCT framework combined with the allmoves-as-first (AMAF) heuristic to select the best child during tree traversal [3]. MoHex-CNN, which won the 13x13 competition of the 20th Computer Olympiad 2017 is a convolutional neural net (CNN) version of MoHex. At each new node of the Monte-Carlo search tree, a policy CNN biases child selection by initializing child visit and win counts with artificial values [4].

Selected Publications

[5]

2000 ...

2005 ...

2010 ...

2015 ...

External Links

References

Up one level