Behavioral Cloning for Simulator Validation
Behavioral cloning is an established technique for creating agent behaviors by replicating patterns of behavior observed in humans or other agents. For pragmatic reasons, behavioral cloning has usually been implemented and tested in simulation environments using a single nonexpert subject. In this paper, we capture behaviors for a team of subject matter experts engaged in real competition (a soccer tournament) rather than participating in a study. From this data set, we create software agents that clone the observed human tactics. We place the agents in a simulation to determine whether increased behavioral realism results in higher performance within the simulation and argue that the transferability of real-world tactics is an important metric for simulator validation. Other applications for validated agents include automated agent behavior, factor analysis for team performance, and evaluation of real team tactics in hypothetical scenarios such as fantasy tournaments.
Unable to display preview. Download preview PDF.
- 1.Aler, R., Garcia, O., Valls, J.M.: Correcting and improving imitation models of humans for robosoccer agents. In: The 2005 IEEE Congress on Evolutionary Computation, vol. 3, pp. 2402–2409 (2005)Google Scholar
- 2.Bratko, I., Urbancic, T., Sammut, C.: Machine Learning and Data Mining: Methods and Applications. In: Behavioural Cloning of Control Skill. John Wiley & Sons Ltd. (1997)Google Scholar
- 3.Cares, J.R.: Agent modeling: the use of agent-based models in military concept development. In: WSC 2002, pp. 935–939 (2002)Google Scholar
- 4.Cost, S., Salzberg, S.: A weighted nearest neighbor algorithm for learning with symbolic features. Machine Learning 10, 57–78 (1993)Google Scholar
- 5.Fuentes, L.M., Velastin, S.A.: People tracking in surveillance applications. In: PETS 2001, Hawaii (2001)Google Scholar
- 6.Gledhill, D.W., Illgen, J.D.: 21st century verification and validation techniques for synthetic training models and simulations. In: Proc. I/ITSEC (1999)Google Scholar
- 7.Kok, J.R., Boer, R.: The incremental development of a synthetic multi-agent system: the UvA Trilearn 2001 robotic soccer simulation team. Master’s thesis. University of Amsterdam, The Netherlands (2002)Google Scholar
- 8.Oh, S., Sastry, S.: A polynomial-time approximation algorithm for joint probabilistic data association. In: Proc. Am. Control Conf. (2005)Google Scholar
- 9.Stone, B.: Serious gaming. Defence Management Journal (2005)Google Scholar
- 10.Suc, D., Bratko, I.: Symbolic and qualitative reconstruction of control skill. Electronic transactions on artificial intelligence, Section B 3, 1–22 (1999)Google Scholar