Monte-Carlo planning for unit control in StarCraft
Zhe Wang, Kien Quang Nguyen, Ruck Thawonmas, Frank Rinaldo · 2012
This paper presents an application of Monte-Carlo planning (MCPlan) to controlling units in a RTS game StarCraft. We apply an ε - greedy algorithm to model the opponent in a simulation for improving MCPlan's performance. Experimental results are provided at the end of this paper, which show the potential of MCPlan in this domain.