Download PDFOpen PDF in browserCreation and Implementation of a Set of Game Strategies Based on Training Neural Networks with Reinforcement LearningEasyChair Preprint 70956 pages•Date: November 28, 2021AbstractThe study explores the problems of reinforcement learning and finding non-obvious play strategies using reinforcement learning. Two approaches to agent training (blind and pattern-based) are considered and implemented. The advantage of the self-learning approach with reinforcement using patterns as applied to a specific game (tic-tac-toe five in a row) is shown. Recorded and analyzed the use of unusual strategies by an agent using a pattern-based approach. Keyphrases: Artificial Intelligence, Reinforcment learning, multi-agent interaction, neural network
|