Trained Behavior Trees: Programming by Demonstration to Support AI Game Designers

Abstract

Programming by demonstration (PbD) has a straightforward application in the development of the artificial intelligence (AI) for nonplayer characters (NPCs) in a video game: a game designer controls the NPC during a training session in the game, and thus demonstrates the expected behavior for that character in different situations. Afterwards, applying some machine learning technique on the traces recorded during the demonstration, an AI for the NPC can be generated. Nevertheless, with this approach, it is very hard for the game designer to fully control the resulting behavior, which is a key requirement for game designers, who are responsible for putting together a fun experience for the player. In this paper, we present trained behavior trees (TBTs). TBTs are behavior trees (BTs) generated from traces obtained in a game through PbD. BTs are a technique widely used for AI game programming that are created and modified through special purpose visual editors. By inducing a BT from a PbD game session, we combine the ease of use of PbD with the ability to fine-tune the learned behavior of BTs. Furthermore, TBTs facilitate the use of BTs by game designers and promote their authoring control on game AI.