Move Evaluation in Go Using Deep Convolutional Neural Networks

Abstract

The game of Go is more challenging than other board games, due to the difficulty of constructing a position or move evaluation function. In this paper we investigate whether deep convolutional networks can be used to directly represent and learn this knowledge. We train a large 12-layer convolutional neural network by supervised learning from a database of human professional games. The network correctly predicts the expert move in 55% of positions, equalling the accuracy of a 6 dan human player. 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 Monte-Carlo tree search that simulates a million positions per move.

Minor edits and included captures in Figure 2

References in corpus (2)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Teaching Deep Convolutional Neural Networks to Play Go

Cited by in corpus (23)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Deep Learning with Differential Privacy
• Learning to Plan Chemical Syntheses
• Dueling Network Architectures for Deep Reinforcement Learning
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• StarCraft II: A New Challenge for Reinforcement Learning
• Learning Multiagent Communication with Backpropagation
• Resource Management in Wireless Networks via Multi-Agent Deep Reinforcement Learning
• Deep Reinforcement Learning from Self-Play in Imperfect-Information Games
• Multi-Objective Deep Reinforcement Learning
• Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks
• Convolutional Invasion and Expansion Networks for Tumor Growth Prediction
• Multi-agent Inverse Reinforcement Learning for Two-person Zero-sum Games
• Strategic Dialogue Management via Deep Reinforcement Learning
• Accelerating Self-Play Learning in Go
• Learning how to Active Learn: A Deep Reinforcement Learning Approach
• ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero
• Artificial Intelligence as Structural Estimation: Economic Interpretations of Deep Blue, Bonanza, and AlphaGo
• Log-law recovery through reinforcement-learning wall model for large-eddy simulation
• Better Computer Go Player with Neural Network and Long-term Prediction
• Multi-Task Learning for Argumentation Mining
• Beyond Monte Carlo Tree Search: Playing Go with Deep Alternative Neural Network and Long-Term Evaluation
• Playing Go without Game Tree Search Using Convolutional Neural Networks