Learning Character Behaviors using Agent Modeling in Games
- Richard Zhao
- Duane Szafron, UofA CS
Our goal is to provide learning mechanisms to game agents so they are capable of adapting to new behaviors based on the actions of other agents. We introduce a new on-line reinforcement learning (RL) algorithm, ALeRT-AM, that includes an agent-modeling mechanism. We implemented this algorithm in BioWare Corp.'s role-playing game, Neverwinter Nights to evaluate its effectiveness in a real game. Our experiments compare agents who use ALeRT-AM with agents that use the non-agent modeling ALeRT RL algorithm and two other non-RL algorithms. We show that an ALeRT-AM agent is able to rapidly learn a winning strategy against other agents in a combat scenario and to adapt to changes in the environment.
Citation
R. Zhao, D. Szafron. "Learning Character Behaviors using Agent Modeling in Games". Artificial Intelligence and Interactive Entertainment Conference (AIIDE), pp 179-185, October 2009.| Keywords: | reinforcement learning, agent modeling, behaviour |
| Category: | In Conference |
| Related Publication(s): | Applying Agent Modeling to Behaviour Patterns of Characters in Story-Based Games |
BibTeX
@incollection{Zhao+Szafron:AIIDE09,
author = {Richard Zhao and Duane Szafron},
title = {Learning Character Behaviors using Agent Modeling in Games},
Pages = {179-185},
booktitle = {Artificial Intelligence and Interactive Entertainment Conference
(AIIDE)},
year = 2009,
}Last Updated: January 18, 2010Submitted by Richard Zhao
