Learning from Demonstration to be a Good Team Member in a Role Playing Game
Michael Silva, Silas McCroskey, Jonathan Rubin, G. Michael Youngblood, Ashwin Ram · 2013
We present an approach that uses learning from demon-stration in a computer role playing game to create a con-troller for a companion team member. We describe a behavior engine that uses case-based reasoning. The be-havior engine accepts observation traces of human play-ing decisions and produces a sequence of actions which can then be carried out by an artificial agent within the gaming environment. Our work focuses on team-based role playing games, where the agents produced by the behavior engine act as team members within a mixed human-agent team. We present the results of a study we conducted, where we assess both the quanti-tative and qualitative performance difference between human-only teams compared with hybrid human-agent teams. The results of our study show that human-agent teams were more successful at task completion and, for some qualitative dimensions, hybrid teams were per-ceived more favorably than human-only teams.