Training a Minesweeper Agent Using a Convolutional Neural Network

Authors:
Open Access
Publisher website
Google Scholar
Abstract
The Minesweeper game is modeled as a sequential decision-making task, for which a neural network architecture, state encoding, and reward function were herein designed. Both a Deep Q-Network (DQN) and supervised learning methods were successfully applied to optimize the training of the game. The experiments were conducted on the AutoDL platform using an NVIDIA RTX 3090 GPU for efficient computation. The results showed that in a 6 × 6 grid with four mines, the DQN model achieved an average win rate of 93.3% (standard deviation: 0.77%), while the supervised learning method achieved 91.2% (standard deviation: 0.9%), both outperforming human players and baseline algorithms and demonstrating high intelligence. The mechanisms of the two methods in the Minesweeper task were analyzed, with the reasons for the faster training speed and more stable performance of supervised learning explained from the perspectives of means–ends analysis and feedback control. Although there is room for improvement in sample efficiency and training stability in the DQN model, its greater generalization ability makes it highly promising for application in more complex decision-making tasks.
Funding Information
  • Young Innovative Talents Project (2019KQNCX013)

This publication has 10 references indexed in Scilit: