Won Joon Yun¹, Sungwon Yi², Joongheon Kim¹
School of Electrical Engineering, Korea University, Seoul, Korea¹
ETRI , DaeJeon, Korea²
In real-time strategy (RTS) game artificial intelligence research, various multi-agent deep reinforcement learning (MADRL) algorithms are widely and actively used nowadays.
Most of the research is based on StarCraft II environment because it is the most well-known RTS games in world-wide.
In our proposed MADRL-based algorithm, distributed MADRL is fundamentally used that is called QMIX. In addition to QMIX-based distributed computation, we consider state categorization which can reduce computational complexity significantly. Furthermore, self-attention mechanisms are used for identifying the relationship among agents in the form of graphs. Based on these approaches, we propose a categorized state graph attention policy (CSGA-policy).
As observed in the performance evaluation of our proposed CSGA-policy with the most well-known StarCraft II simulation environment, our proposed algorithm works well in various settings, as expected.
[site]