Behavioral Animation of Autonomous Virtual Agents Helped by Reinforcement Learning

  • Toni Conde
  • William Tambellini
  • Daniel Thalmann
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2792)

Abstract

Our research focuses on the behavioral animation of virtual humans who are capable of taking actions by themselves. In this paper we will deal more specifically with Reinforcement Learning methodologies, which integrate in an original way the RL agent and the Autonomous Virtual Agent in a Virtual Environment. With the help of a Virtual Environment in the form of a town, we shall demonstrate that it is indeed the learning process and not the optimization of RL, which is used by the AVAs.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Guye-Vuillème, A., Thalmann, D.: A High-level Architecture for Believable Social Agents. VR Journal 5, 95–106 (2001)Google Scholar
  2. 2.
    Kallmann, M., de Sevin, E., Thalmann, D.: Constructing Virtual Human Life Simulations. In: AVATARS Workshop, Lausanne, Switzerland (2000)Google Scholar
  3. 3.
    Monzani, J.S., Caicedo, A., Thalmann, D.: Integrating Behavioural Animation Techniques. In: Proc. Eurographics 2001 (2001)Google Scholar
  4. 4.
    Whitehead, S., Karlsson, J., Tenenberg, J.: Learning Multiple Goal Behavior via Task Decomposition and Dynamic Policy Merging. In: Connell, Mahadevan (eds.) Robot Learning, Kluwer Academic Publishers, Dordrecht (1993)Google Scholar
  5. 5.
    Sutton, R.S., Santamaria, J.-C.: A Standard Interface for Reinforcement Learning Software in C++, version 1.1Google Scholar
  6. 6.
    Sutton, R.S., Barto, G.: Reinforcement Learning: an Introduction. MIT Press, Cambridge (1998)Google Scholar
  7. 7.
    Kaebling, L.P., Littman, M., Moore, A.: Reinforcement Learning: a Survey. JAIR 4, 237–285 (1996)Google Scholar
  8. 8.
    Ponder, M., Papagiannakis, G., Molet, T., Magnenat-Thalmann, N., Thalmann, D.: VHD++ Development Framework: Towards Extendible, Component Based VR/AR Simulation Engine Featuring Advanced Virtual Character Technologies. IEEE Virtual Reality (2003)Google Scholar
  9. 9.
    Elizabeth, A.: Employing AI methods to control the behavior of animated interface agents. Applied Artificial Intelligence 13(4-5), 45–448 (1999)Google Scholar
  10. 10.
    Langton, C.: Artificial Life. Addison-Wesley, Reading (1989)Google Scholar
  11. 11.
    Steels, L., Brooks, R.-A.: The Artificial Life Role to Artificial Intelligence: Building Embodied Situated Agents. Lawrence Ferlbaum Associates, Mahwah (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Toni Conde
    • 1
  • William Tambellini
    • 1
  • Daniel Thalmann
    • 1
  1. 1.Virtual Reality LabSwiss Federal Institute of Technology (EPFL)LausanneSwitzerland

Personalised recommendations