Learning Macromanagement in StarCraft from Replays using Deep Learning
This addresses the problem of reducing reliance on hand-crafted modules for AI in StarCraft, though it is incremental as it does not surpass the best hand-crafted strategies.
The paper tackled learning macromanagement decisions in StarCraft from replays using deep learning, achieving top-1 and top-3 error rates of 54.6% and 22.9% in predicting build actions and integrating the network into a bot to outperform the built-in Terran bot.
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.