Filters








23,886 Hits in 5.1 sec

Move Evaluation in Go Using Deep Convolutional Neural Networks [article]

Chris J. Maddison, Aja Huang, Ilya Sutskever, David Silver
2015 arXiv   pre-print
In this paper we investigate whether deep convolutional networks can be used to directly represent and learn this knowledge.  ...  When the trained convolutional network was used directly to play games of Go, without any search, it beat the traditional search program GnuGo in 97% of games, and matched the performance of a state-of-the-art  ...  In this paper we address these fundamental questions of representation and learning of Go knowledge, by using a deep convolutional neural network (CNN).  ... 
arXiv:1412.6564v2 fatcat:twhvr332fzgtlk36ttij5cp2pi

Suggesting Moving Positions in Go-Game with Convolutional Neural Networks Trained Data

Hoang Huu Duc, Lee Jihoon, Jung Keechul
2016 International Journal of Hybrid Information Technology  
In our work, we suggest the next move based on Convolutional Neural Networks (CNNs) and make evaluations and comparisons to gamers separate in 3 ranks (levels).  ...  This technique allows Go-game program play the game without searching as traditional program but trained by convolutional neural networks.  ...  We resolve this problem using a deep convolutional neural network (CNN).  ... 
doi:10.14257/ijhit.2016.9.4.05 fatcat:5hhbkmhn3beuppuch3gexefsai

Beyond Monte Carlo Tree Search: Playing Go with Deep Alternative Neural Network and Long-Term Evaluation [article]

Jinzhuo Wang, Wenmin Wang, Ronggang Wang, Wen Gao
2017 arXiv   pre-print
The first part is a novel deep alternative neural network (DANN) used to generate candidates of next move.  ...  Compared with existing deep convolutional neural network (DCNN), DANN inserts recurrent layer after each convolutional layer and stacks them in an alternative manner.  ...  Conclusion In this work, we have proposed a computer Go system based on a novel deep alternative neural networks (DANN) and long-term evaluation (LTE).  ... 
arXiv:1706.04052v1 fatcat:x34zvwjezva6pjmhi6rtagp6te

Convolutional Monte Carlo Rollouts in Go [article]

Peter H. Jin, Kurt Keutzer
2015 arXiv   pre-print
In this work, we present a MCTS-based Go-playing program which uses convolutional networks in all parts.  ...  Our method performs MCTS in batches, explores the Monte Carlo search tree using Thompson sampling and a convolutional network, and evaluates convnet-based rollouts on the GPU.  ...  deep convolutional neural nets with MCTS.  ... 
arXiv:1512.03375v1 fatcat:g32plk7kzzfahd33ky7x3r2fbu

Residual Networks for Computer Go

Tristan Cazenave
2018 IEEE Transactions on Games  
Deep Learning for the game of Go recently had a tremendous success with the victory of AlphaGo against Lee Sedol in March 2016.  ...  We propose to use residual networks so as to improve the training of a policy network for computer Go.  ...  ACKNOWLEDGMENT The author would like to thank Nvidia and Philippe Vandermersch for providing a K40 GPU that was used in some experiments.  ... 
doi:10.1109/tciaig.2017.2681042 fatcat:gzgty6ddnrcuhfath4v2wz67ci

Mastering the game of Go without human knowledge

David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, Yutian Chen, Timothy Lillicrap (+5 others)
2017 Nature  
Recently, AlphaGo became the first program to defeat a world champion in the game of Go. The tree search in AlphaGo evaluated positions and selected moves using deep neural networks.  ...  AlphaGo Fan utilised two deep neural networks: a policy network that outputs move probabilities, and a value network that outputs a position evaluation.  ...  Move evaluation in Go using deep convolutional neural networks. In International Conference on Learning Representations (2015). 31. Clark, C. & Storkey, A. J.  ... 
doi:10.1038/nature24270 pmid:29052630 fatcat:h2n334a2ejfxtknx67kbiaswfq

Mobile Networks for Computer Go [article]

Tristan Cazenave
2020 arXiv   pre-print
The architecture of the neural networks used in Deep Reinforcement Learning programs such as Alpha Zero or Polygames has been shown to have a great impact on the performances of the resulting playing engines  ...  For example the use of residual networks gave a 600 ELO increase in the strength of Alpha Go.  ...  legal moves in Go.  ... 
arXiv:2008.10080v1 fatcat:aaax6k426jd4tkaqcgd5st4cuu

Training Deep Convolutional Neural Networks to Play Go

Christopher Clark, Amos J. Storkey
2015 International Conference on Machine Learning  
Following this sentiment, we train deep convolutional neural networks to play Go by training them to predict the moves made by expert Go players.  ...  Our convolutional neural networks can consistently defeat the well known Go program GNU Go and win some games against state of the art Go playing program Fuego while using a fraction of the play time.  ...  Previous Work Previous work in move prediction for Go typically made use of feature construction or shallow neural networks.  ... 
dblp:conf/icml/ClarkS15 fatcat:egl2rmtband5xe3bag7gemrd64

Research on integrated computer game algorithm for dots and boxes

Shuqin Li, Yipeng Zhang, Meng Ding, Pengcheng Dai
2020 The Journal of Engineering  
This article first proposes a deep convolutional neural network model based on dots and boxes, including deep value network and deep strategy network, focusing on situation assessment and strategy recommendation  ...  Then, using the Monte Carlo Tree Search (MCTS) algorithm as a framework, deep value network integrated MCTS algorithm and deep strategy network integrated MCTS algorithm are proposed.  ...  In this paper, the deep neural network model is used as a regression to evaluate the quality of both sides of players in real-time, and to evaluate the current situation of all Design and implementation  ... 
doi:10.1049/joe.2019.1185 fatcat:y7q2n3khizc4lc7e74y72uj4se

Teaching Deep Convolutional Neural Networks to Play Go [article]

Christopher Clark, Amos Storkey
2015 arXiv   pre-print
Following this sentiment, we train deep convolutional neural networks to play Go by training them to predict the moves made by expert Go players.  ...  Our convolutional neural networks can consistently defeat the well known Go program GNU Go, indicating it is state of the art among programs that do not use Monte Carlo Tree Search.  ...  In this work we train deep convolutional neural networks (DCNNs) to detect strong moves within a Go position by training them on move prediction, the task of predicting where expert human players would  ... 
arXiv:1412.3409v2 fatcat:yi6n5s4o35dojff53x2oezopmu

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan (+1 others)
2018 Science  
By contrast, the AlphaGo Zero program recently achieved superhuman performance in the game of Go by reinforcement learning from self-play.  ...  Starting from random play and given no domain knowledge except the game rules, AlphaZero convincingly defeated a world champion program in the games of chess and shogi (Japanese chess), as well as Go.  ...  Recently, the AlphaGo Zero algorithm achieved superhuman performance in the game of Go by representing Go knowledge with the use of deep convolutional neural networks (7, 8) , trained solely by reinforcement  ... 
doi:10.1126/science.aar6404 pmid:30523106 fatcat:3ojohsnggndppnfm5akucp7pve

Training of a deep learning algorithm for quadcopter gesture recognition

Calvin Ng
2020 International Journal of Advanced Trends in Computer Science and Engineering  
Also, deep learning in the form of a convolutional neural network is a more compatible approach to gesture recognition than other methods.  ...  The neural network was coded in Python using the Keras library and was trained on a laptop computer.  ...  DEEP CONVOLUTIONAL NEURAL NETWORKS Convolutional Neural Networks are machine learning approaches that are based on biology.  ... 
doi:10.30534/ijatcse/2020/32912020 fatcat:rijkziismvbn7cp4m5rs5wsoi4

Mastering the game of Go with deep neural networks and tree search

David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe (+8 others)
2016 Nature  
We introduce a new approach to computer Go that uses value networks to evaluate board positions and policy networks to select moves.  ...  Recently, deep convolutional neural networks have achieved unprecedented performance in visual domains: for example image classification 17 , face recognition 18 , and playing Atari games 19 .  ...  in small-board Go 27, 28, 46 using convolutional networks.  ... 
doi:10.1038/nature16961 pmid:26819042 fatcat:hhxixsirtjairjuwqivmi3gcga

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
Go, and convincingly defeated a world-champion program in each case.  ...  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.  ...  Move evaluation in Go using deep convolutional neural networks. In International Conference on Learning Representations, 2015. 23. Tony Marsland. Computer chess methods. In S.  ... 
arXiv:1712.01815v1 fatcat:flj56adezzf6xepdezevbo24xq

Deep Learning and the Game of Checkers

Jan Popic, Borko Boskovic, Janez Brest
2021 The MENDEL Soft Computing journal : International Conference on Soft Computing MENDEL  
Any human influence or knowledge is removed by generating needed data, for training neural network, using self-play.  ...  We compare different obtained versions of neural networks and their progress in playing the game of Checkers. Every new version of neural network represented a better player.  ...  Deepminds programs AlphaGo [7] , AlphaGo Zero [9] and Alpha Zero [8] are one such example of using a deep convolutional neural networks as part of a bigger algorithm that can learn to play a game  ... 
doi:10.13164/mendel.2021.2.001 doaj:672aad335e4b4eeeb9e98ab5a8609bdb fatcat:rzo56qeenvbmpc7dcs2a7y6kam
« Previous Showing results 1 — 15 out of 23,886 results