Modelling Human-like Behavior through Reward-based Approach in a First-Person Shooter Game

Ch. 3. P. 24–33.

Makarov I., Peter Zyuzin, Pavel Polyakov, Mikhail Tokmakov, Olga Gerasimova, Ivan Guschenko-Cheverda, Maxim Uriev

We present two examples of how human-like behavior can be implemented in a model of computer player to improve its characteristics and decision-making patterns in video game. At first, we describe a reinforcement learning model, which helps to choose the best weapon depending on reward values obtained from shooting combat situations. Secondly, we consider an obstacle avoiding path planning adapted to the tactical visibility measure. We describe an implementation of a smoothing path model, which allows the use of penalties (negative rewards) for walking through ``bad'' tactical positions. We also study algorithms of path finding such as improved I-ARA* search algorithm for dynamic graph by copying human discrete decision-making model of reconsidering goals similar to Page-Rank algorithm. All the approaches demonstrate how human behavior can be modeled in applications with significant perception of intellectual agent actions.

Keywords: reinforcement learning, Game Artificial Intelligence, path planning, video games, Human-like Behavior, Graph-based Search

In book

Proceedings of the Third Workshop on Experimental Economics and Machine Learning (EEML 2016), Moscow, Russia, July 18, 2016

Vol. 1627. , Aachen: CEUR Workshop Proceedings, 2016.