Learning Macromanagement in StarCraft from Replays using Deep Learning

TL;DR

This paper demonstrates that deep learning can effectively learn macromanagement decisions in StarCraft directly from game replays, enabling the development of more adaptable and less hand-crafted AI agents.

Contribution

It introduces a novel approach of training neural networks on replays to learn macromanagement, outperforming built-in bots and paving the way for future reinforcement learning improvements.

Findings

Neural networks achieved 54.6% top-1 error in predicting build actions.

The system outperforms the game's built-in Terran bot.

The approach is the first to learn macromanagement directly from replays in StarCraft.

Abstract

The real-time strategy game StarCraft has proven to be a challenging environment for artificial intelligence techniques, and as a result, current state-of-the-art solutions consist of numerous hand-crafted modules. In this paper, we show how macromanagement decisions in StarCraft can be learned directly from game replays using deep learning. Neural networks are trained on 789,571 state-action pairs extracted from 2,005 replays of highly skilled players, achieving top-1 and top-3 error rates of 54.6% and 22.9% in predicting the next build action. By integrating the trained network into UAlbertaBot, an open source StarCraft bot, the system can significantly outperform the game's built-in Terran bot, and play competitively against UAlbertaBot with a fixed rush strategy. To our knowledge, this is the first time macromanagement tasks are learned directly from replays in StarCraft. While the best hand-crafted strategies are still the state-of-the-art, the deep network approach is able to express a wide range of different strategies and thus improving the network's performance further with deep reinforcement learning is an immediately promising avenue for future research. Ultimately this approach could lead to strong StarCraft bots that are less reliant on hard-coded strategies.