Macro action selection with deep reinforcement learning in StarCraft

December 02, 2018 Β· Declared Dead Β· πŸ› Artificial Intelligence and Interactive Digital Entertainment Conference

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Sijia Xu, Hongyu Kuang, Zhi Zhuang, Renjie Hu, Yang Liu, Huyang Sun arXiv ID 1812.00336 Category cs.AI: Artificial Intelligence Citations 30 Venue Artificial Intelligence and Interactive Digital Entertainment Conference Last Checked 4 months ago
Abstract
StarCraft (SC) is one of the most popular and successful Real Time Strategy (RTS) games. In recent years, SC is also widely accepted as a challenging testbed for AI research because of its enormous state space, partially observed information, multi-agent collaboration, and so on. With the help of annual AIIDE and CIG competitions, a growing number of SC bots are proposed and continuously improved. However, a large gap remains between the top-level bot and the professional human player. One vital reason is that current SC bots mainly rely on predefined rules to select macro actions during their games. These rules are not scalable and efficient enough to cope with the enormous yet partially observed state space in the game. In this paper, we propose a deep reinforcement learning (DRL) framework to improve the selection of macro actions. Our framework is based on the combination of the Ape-X DQN and the Long-Short-Term-Memory (LSTM). We use this framework to build our bot, named as LastOrder. Our evaluation, based on training against all bots from the AIIDE 2017 StarCraft AI competition set, shows that LastOrder achieves an 83% winning rate, outperforming 26 bots in total 28 entrants.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ‘» Ghosted