Training Deep Convolutional Neural Networks to Play Go

By Christopher Clark, Amos J. Storkey. 2015

180 citations recorded by the source corpus.

Subfields: Reinforcement Learning, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

In Model Architectures

Citations in the corpus

Planning chemical syntheses with deep neural networks and symbolic AI (2017, methodology): “[31–33] In this work, inspired by the recent progress in Go culminating in AlphaGo,[31] we combine three different neural networks (3N) together with MCTS to perform chemical synthesis planning (3N-MCTS).”
Deep Reinforcement Learning from Self-Play in Imperfect-Information Games (2016, background): “In computer Go, Maddison et al. (2015) and Clark and Storkey (2015) trained deep neural networks from data of expert human play.”
Exploiting Cyclic Symmetry in Convolutional Neural Networks (2016, background): “Clark & Storkey (2015) force the ﬁl-ters of convolutional layers to exhibit dihedral symmetry through weight sharing, which means the resulting feature maps will necessarily be invariant.”
Adversarial Diversity and Hard Positive Generation (2016, background): “Deep neural networks are powerful learning models which have been successfully applied to vision, speech and many other tasks [9, 11, 18, 19, 10, 20, 4, 3].”
Prediction of interresidue contacts with DeepMetaPSICOV in CASP13 (2019, neutral): “Similar approaches have been used in otherwork.(11,12)”
Automatically Designing CNN Architectures Using Genetic Algorithm for Image Classification (2018, background): “C ONVOLUTIONAL Neural Networks (CNNs), as the dominant technique of deep learning [1], have shown remarkable superiority in various real-world applications over most machine learning approaches [2], [3], [4], [5].”
Augmenting Image Classifiers Using Data Augmentation Generative Adversarial Networks (2018, background): “They have been demonstrated in variety of domains [12] spanning from image classification [25, 17, 16, 18, 21], machine translation [44], natural language processing [12], speech recognition [19], and synthesis [42], learning from human play [6] and reinforcement learning [27, 35, 10, 40, 13] among ”
ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero (2019, background): “Go’s square grid game board and the spatial locality of moves naturally suggest the use of convolutional architectures, trained on historical human games (Clark & Storkey, 2015; Maddi-son et al., 2015; Tian & Zhu, 2015).”
Better Computer Go Player with Neural Network and Long-term Prediction (2015, methodology): “Fortunately, recent works [Maddison et al. (2015); Clark & Storkey (2015)] in Computer Go have shown that the Go board situation could be deciphered with Deep Convolutional Neural Network (DCNN).”
Automatically Designing CNN Architectures Using the Genetic Algorithm for Image Classification (2018, background): “C ONVOLUTIONAL neural networks (CNNs), as the dominant technique of deep learning [1], have shown remarkable superiority in various real-world applications over most machine-learning approaches [2]–[5].”
Deep Learning for Predicting Human Strategic Behavior (2016, methodology): “Notable exceptions are Clark and Storkey [4] and the policy network used in Silver et al. [17]’s work in predicting the actions of human players in Go.”
Completely Automated CNN Architecture Design Based on Blocks (2020, unknown): “Speciﬁcally, the pooling layers in CNNs perform the dimension reduction on their input data, and the most commonly used pooling operation is to halve the input size, which can be seen from the state-of-the-art CNNs [2]–[5], [17], [18].”
Imitation Learning (2017, background): “In recent attempts to teach an agent to play the board game “Go” [Clark and Storkey 2015; Silver et al. 2016], the board was divided into a 19 × 19 grid.”
Neural Networks and Deep Learning (2018, unknown): “The use of convolutional neural networks for playing the game of Go has been explored in [73, 307, 481].”
Mastering the game of Go with deep neural networks and tree search (2016, methodology): “For the first stage of the training pipeline, we build on prior work on predicting expert moves in the game of Go using supervised learning 13,21–24 .”
Neural network-based clustering using pairwise constraints (2015, background): “…(Krizhevsky et al., 2012), pixel-level labeling for image segmentation (Long et al., 2015; Zheng et al., 2015), robot arm control (Levine et al., 2015), speech recognition (Graves & Jaitly, 2014), playing Atari games (Mnih et al., 2015) and Go (Clark & Storkey, 2015; Silver et al., 2016).”