Learning Hierarchical Skills for Game Agents from Video of Human Behavior
Nan Li, David John Stracuzzi, Gary Cleveland, Pat Langley, Tolga Könik, Dan Shapiro, Kamal Ali, Matthew Molineaux, David W. Aha · 2009
Developing autonomous agents for computer games is often a lengthy and expensive undertak-ing that requires manual encoding of detailed and complex knowledge. In this paper we show how to acquire hierarchical skills for controlling a team of simulated football players by observing video of college football play. We then demonstrate the re-sults in the Rush 2008 football simulator, showing that the learned skills have high fidelity with respect to the observed video and are robust to changes in the environment. Finally, we conclude with discus-sions of this work and of possible improvements. 1