3,081 Hits in 8.4 sec

The ACG 2019 Conference

Tristan Cazenave, Jaap van den Herik, Abdallah Saffidine, I-Chen Wu
2020 ICGA Journal  
In this conference 19 papers were submitted. Each paper was sent to three reviewers. The Program Committee accepted 12 papers for presentation at the conference and publication in these proceedings.  ...  The two-step process is meant (a) to give authors the opportunity to include the results of the fruitful discussion after the lecture in their paper, and (b) to maintain the high-quality threshold of the  ...  The authors are interested in programs that can entertain or teach human players. The programs automatically generate puzzles so that human players improve at playing the game of Tetris.  ... 
doi:10.3233/icg-200171 fatcat:n3sxo75755fd5ehe63ldk52jra

Data analytics on the board game Go for the discovery of interesting sequences of moves in joseki

Carson K. Leung, Felix Kanke, Alfredo Cuzzocrea
2018 Procedia Computer Science  
In this article, we focus on the board game of Go, which is a popular two-player strategic board game. Due to its popularity, many people are studying sequences of moves in games (i.e., joseki).  ...  In this article, we focus on the board game of Go, which is a popular two-player strategic board game. Due to its popularity, many people are studying sequences of moves in games (i.e., joseki).  ...  Fig. 1 shows the first 22 moves of a game between KE Jie (the top player in the world at the time of the game) and AlphaGo.  ... 
doi:10.1016/j.procs.2018.08.017 fatcat:vfxbgqzrejdvbd7fxspgnv4dia

MP-Draughts: A multiagent reinforcement learning system based on MLP and Kohonen-SOM neural networks

Valquiria Aparecida Rosa Duarte, Rita Maria Silva Julian, Ayres Roberto Araujo Barcelos, Alana Bueno Otsuka
2009 2009 IEEE International Conference on Systems, Man and Cybernetics  
This paper shows that such a strategy significantly improves the general performance of the player agents.  ...  in final phases of a game, even being in advantageous situation compared to its opponent (for instance, getting into endgame loops).  ...  In addition, it has access to a library of opening moves obtained from games played by grand masters and to an endgame database, which is a computer-generated collection of positions with a proven game-theoretic  ... 
doi:10.1109/icsmc.2009.5345960 dblp:conf/smc/DuarteJBO09 fatcat:tpkdv3k2sjcjfipm6wcev6zl2y

Ensemble Determinization in Monte Carlo Tree Search for the Imperfect Information Card Game Magic: The Gathering

Peter I. Cowling, Colin D. Ward, Edward J. Powley
2012 IEEE Transactions on Computational Intelligence and AI in Games  
Additionally we deconstruct the move generation procedure into a binary yes/no decision tree and apply MCTS to this finer grained decision process.  ...  In this paper, we examine the use of Monte Carlo Tree Search (MCTS) for a variant of one of the most popular and profitable games in the world: the card game Magic: The Gathering (M:TG).  ...  In summary, the following move pruning strategies were investigated: 1) No move pruning. At this level we consider all possible moves available to each player. 2) Non-land pruning.  ... 
doi:10.1109/tciaig.2012.2204883 fatcat:eehhxpg72ffn5ehfyuoa7mgcua

Tree Pruning for New Search Techniques in Computer Games

Kieran Greer
2013 Advances in Artificial Intelligence  
Finally, a completely new search process will be suggested for computer chess or games in general.  ...  This paper proposes a new mechanism for pruning a search game tree in computer chess. The algorithm stores and then reuses chains or sequences of moves, built up from previous searches.  ...  It can represent all of the moves in a single 64-square board array.  ... 
doi:10.1155/2013/357068 fatcat:vfxky74myjhudcd5d7xmwvjtmm

Automated Discovery of Search-Extension Features [chapter]

Pálmi Skowronski, Yngvi Björnsson, Mark H. M. Winands
2010 Lecture Notes in Computer Science  
In this work we introduce Gradual Focus, an algorithm for automatically discovering interesting move categories for selective search extensions.  ...  Empirical data is presented for the game Breakthrough showing that Gradual Focus looks at two orders of magnitude fewer combinations than a brute force method does, while preserving good precision and  ...  In this work we investigate ways for automatically discovering useful move categories for use in game-playing programs.  ... 
doi:10.1007/978-3-642-12993-3_17 fatcat:zbht23ajjbhdtbltu5q6bf5exi

Guiding Multiplayer MCTS by Focusing on Yourself

Hendrik Baier, Michael Kaisers
2020 2020 IEEE Conference on Games (CoG)  
In n-player sequential move games, the second rootplayer move appears at tree depth n + 1.  ...  This simplifying model enables Alpha-Beta pruning, thus allowing the search to reach follow-up root player moves at greater search depths.  ...  The most interesting and challenging goal here might be the automatic end-to-end learning of an optimal online generalization technique. fully expanded game tree of a three-player toy game.  ... 
doi:10.1109/cog47356.2020.9231603 dblp:conf/cig/BaierK20 fatcat:mswyxiqn7zbe3fh73iwawpa2va

Improving heuristic mini-max search by supervised learning

Michael Buro
2002 Artificial Intelligence  
These general methods represent the state-of-the-art in computer Othello programming and begin to attract researchers in related fields.  ...  This approach allows an automatic, data driven exploration of the feature space.  ...  The game ends when neither player has a legal move, in which case the player with the most discs on the board has won.  ... 
doi:10.1016/s0004-3702(01)00093-5 fatcat:vzfhumuzyngrjihjr2mdbdhdsm

The structure of games

David M. Kaiser
2005 Proceedings of the 43rd annual southeast regional conference on - ACM-SE 43  
The system automatically generates evaluation functions from game descriptions given in the Game Description Language.  ...  Chapter 6 presents Automatic Theorem Proving which will help the reader in the sections discussing the design of OGRE, our General Game Playing system.  ...  /* * The Game of TicTacToe */ /***************************************************************** *** DEFINITION *****************************************************************/ % --initVisible(+location  ... 
doi:10.1145/1167350.1167378 dblp:conf/ACMse/Kaiser05 fatcat:oympuuxgeneypkgzb2ipobsw2i

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm [article]

David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis
2017 arXiv   pre-print
In this paper, we generalise this approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance in many challenging domains.  ...  In contrast, the AlphaGo Zero program recently achieved superhuman performance in the game of Go, by tabula rasa reinforcement learning from games of self-play.  ...  In AlphaGo Zero, self-play games were generated by the best player from all previous iterations.  ... 
arXiv:1712.01815v1 fatcat:flj56adezzf6xepdezevbo24xq

Biasing MCTS with Features for General Games [article]

Dennis J. N. J. Soemers, Éric Piette, Cameron Browne
2019 arXiv   pre-print
This paper proposes using a linear function approximator, rather than a deep neural network (DNN), to bias a Monte Carlo tree search (MCTS) player for general games.  ...  We evaluate the playing strength of an MCTS player biased by learnt features against a standard upper confidence bounds for trees (UCT) player in multiple different board games, and demonstrate significantly  ...  Just like self-play games, evaluation games allow for 5 seconds of thinking time per move, and are automatically declared a tie after 100 moves.  ... 
arXiv:1903.08942v1 fatcat:7thq7n6eibgvlp62asqzo55xbu

Conditional combinatorial games and their application to analyzing capturing races in Go

M Müller
2003 Information Sciences  
However, play in a CCG depends on its global context: certain moves are legal only if a nonlocal context condition is currently true.  ...  We introduce a general framework for analyzing semeai, which is based on CCG and on an extension called liberty count games.  ...  As in normal Nim, players remove a number of tokens from a single heap at each move. 2. Additionally, after each move the total number of tokens in the whole game must be a prime number.  ... 
doi:10.1016/s0020-0255(03)00050-1 fatcat:ye4civhczfbt7jgez6rmcyxmje

Monte-Carlo Go Reinforcement Learning Experiments

Bruno Bouzy, Guillaume Chaslot
2006 2006 IEEE Symposium on Computational Intelligence and Games  
In a previous study, Monte-Carlo was associated with domain-dependent knowledge in the Go-playing program Indigo. In 2003, a 3x3 pattern database was built manually.  ...  This paper explores the possibility of using reinforcement learning to automatically tune the 3x3 pattern urgencies.  ...  Fig. 1 . 1 Progressive pruning: the root is expanded (1). Random games start on children (2) . After several random games, some moves are pruned (3) .  ... 
doi:10.1109/cig.2006.311699 dblp:conf/cig/BouzyC06 fatcat:ly3lnjdpgnezpmkhdgr2diokxe

Neural Learning of Heuristic Functions for General Game Playing [chapter]

Leo Ghignone, Rossella Cancelliere
2016 Lecture Notes in Computer Science  
The proposed model represents an original approach to general game playing, and aims at creating a player able to develop a strategy using as few requirements as possible, in order to achieve the maximum  ...  generality.  ...  The moves of our NHB-player in the space of all possible game states are chosen using a minimax algorithm with alpha-beta pruning and iterative deepening: this method is described in Section 2.  ... 
doi:10.1007/978-3-319-51469-7_7 fatcat:t43qa53fanej3ggq6mdvftafu4

A Survey of Monte Carlo Tree Search Methods

Cameron B. Browne, Edward Powley, Daniel Whitehouse, Simon M. Lucas, Peter I. Cowling, Philipp Rohlfshagen, Stephen Tavener, Diego Perez, Spyridon Samothrakis, Simon Colton
2012 IEEE Transactions on Computational Intelligence and AI in Games  
It has received considerable interest due to its spectacular success in the difficult problem of computer Go, but has also proved beneficial in a range of other domains.  ...  Monte Carlo Tree Search (MCTS) is a recently proposed search method that combines the precision of tree search with the generality of random sampling.  ...  General Game Playing General Game Players (GGPs) are software agents intended to play a range of games well rather than any single game expertly.  ... 
doi:10.1109/tciaig.2012.2186810 fatcat:z2o6xdkkjvhf3k6hybw65o5r44
« Previous Showing results 1 — 15 out of 3,081 results