Learnable behavioural model for autonomous virtual agents: low-level learning

In this paper, we propose a new integration approach for simulation and behaviour in the learning context that is able to coherently manage the shared virtual environment for the simulation of autonomous virtual agents. Our low-level learning technique has proved fast, simple and robust. It is also able to automatically learn behavioural models for difficult tasks. Thus, we believe it will be more useful to the computer graphics community than a technique based on the classical Q-learning approach. The results are illustrated in two case studies that require effective coordination of behaviours. Categories and Subject Descriptors I.2.6 [Artificial Intelligence]: Learning; I.3.6 [Computer Graphics]: Methodology and Techniques

• Type: Conference
• Year: 2006
• Where: ATAL
• Authors: Toni Conde, Daniel Thalmann
• Keywords: ATAL 2006, Computer Graphics, Computer Graphics Community, Intelligent Agents, Low-level Learning Technique