Continuing my interest in RTS AI, today I came across the PhD thesis of Prof. Churchill, whom I read his some of his interesting works recently. In this paper, Prof. Churchill amalgamates his works on RTS AI and introduces possible future research and considerations.
Douglas Yuen, Markus Santoso, Stephen Cartwright, Christian Jacob
Real-time strategy (RTS) video games are known for being one of the most complex and strategic games for humans to play. With a unique combination of strategic thinking and dextrous mouse movements, RTS games make for a very intense and exciting game-play experience. In recent years the games AI research community has been increasingly drawn to the field of RTS AI research due to its challenging sub-problems and harsh real-time computing constraints. With the rise of e-Sports and professional human RTS gaming, the games industry has become very interested in AI techniques for helping design, balance, and test such complex games. In this thesis we will introduce and motivate the main topics of RTS AI research, and identify which areas need the most improvement. We then describe the RTS AI research we have conducted, which consists of five major contributions. First, our depth-first branch and bound build-order search algorithm, which is capable of producing professional human-quality build-orders in real-time, and was the first heuristic search algorithm to be used on-line in a starcraft AI competition setting. Second, our RTS combat simulation system: SparCraft, which contains three new algorithms for unit micromanagement (Alpha-Beta Considering Durations (ABCD), UCT Considering Durations (UCT-CD) and Portfolio Greedy Search), each outperforming the previous state-of-the-art. Third, Hierarchical Portfolio Search for games with large search spaces, which was implemented as the AI system for the online strategy game Prismata by Lunarch Studios. Fourth, UAlbertaBot: our starcraft AI bot which won the 2013 AIIDE starcraft AI competition. And fifth: our tournament managing software which is currently used in all three major starcraft AI competitions.
This paper can be used as a great introduction to the research of RTS AI, as it outlines all the sub-problems that RTS Bots need to solve, as well as introduces the necessary terms.
I didn’t read all of it due to the technicality of some of the chapters, but I benefited most from getting a holistic view of the current state of the research, as the paper publication date is 2017.
The paper has also described the possible applications of smart RTS Bots, and one of the interesting applications is helping game designers in balancing the game, and I can see this applied by giving the designer the tools to play-test on the fly using bots the resemble players of different experiences. Then, the game designer could evaluate the playtests to tweak and balance the values, or even better, let an AI system find the optimal balanced values.
Lastly, the paper has indicated directions for possible future research, including the interesting problem of Goal-less Build Order Search. In this problem, the build-order optimization algorithm is not only responsible for finding the action to achieve the goal, but also to decide the goal itself based on optimizing certain combat-based values.
The paper can be accessed at: http://www.cs.mun.ca/~dchurchill/pdf/DavidChurchill_phd_thesis.pdf