CAPIR: Collaborative Action Planning with Intention Recognition

TL;DR

This paper introduces CAPIR, a decision-theoretic approach for creating non-player characters that assist humans in collaborative games by recognizing their intentions and decomposing complex tasks into manageable subtasks.

Contribution

The paper presents a scalable method combining intention recognition and task decomposition for NPC assistance in complex collaborative games.

Findings

Effective assistance at near-human levels

Scalable approach for complex game states

Improved NPC collaboration performance

Abstract

We apply decision theoretic techniques to construct non-player characters that are able to assist a human player in collaborative games. The method is based on solving Markov decision processes, which can be difficult when the game state is described by many variables. To scale to more complex games, the method allows decomposition of a game task into subtasks, each of which can be modelled by a Markov decision process. Intention recognition is used to infer the subtask that the human is currently performing, allowing the helper to assist the human in performing the correct task. Experiments show that the method can be effective, giving near-human level performance in helping a human in a collaborative game.