StarCraft II Build Order Optimization using Deep Reinforcement Learning\n and Monte-Carlo Tree Search

2020/06/12 by Islam Elnabarawy, Elnabarawy, Islam, Kristijana Arroyo +3 · 1 citation
Computer Science · Psychology · Social Sciences · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Games #Digital Games and Media #Educational Games and Gamification #FOS: Computer and information sciences #Machine Learning (cs.LG) #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.2006.10525

openalex publication_date 2020/06/12 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28

Abstract

The real-time strategy game of StarCraft II has been posed as a challenge for\nreinforcement learning by Google's DeepMind. This study examines the use of an\nagent based on the Monte-Carlo Tree Search algorithm for optimizing the build\norder in StarCraft II, and discusses how its performance can be improved even\nfurther by combining it with a deep reinforcement learning neural network. The\nexperimental results accomplished using Monte-Carlo Tree Search achieves a\nscore similar to a novice human player by only using very limited time and\ncomputational resources, which paves the way to achieving scores comparable to\nthose of a human expert by combining it with the use of deep reinforcement\nlearning.\n

Citations

• StarCraft II: A New Challenge for Reinforcement Learning
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Cited by

• Code Driven Planning with Domain-Adaptive Critic

Related

• SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II
• StarCraft II: A New Challenge for Reinforcement Learning
• Applying supervised and reinforcement learning methods to create\n neural-network-based agents for playing StarCraft II
• Modular Architecture for StarCraft II with Deep Reinforcement Learning
• Learning Macromanagement in StarCraft from Replays using Deep Learning