hal-00752841, version 1
Special Tactics: a Bayesian Approach to Tactical Decision-making
Gabriel Synnaeve
1, 2Pierre Bessière a, 1, 2
Proceedings of the IEEE Conference on Computational Intelligence and Games (2012) 978-1-4673-1194-6/12/ 409-416
Résumé : We describe a generative Bayesian model of tactical attacks in strategy games, which can be used both to predict attacks and to take tactical decisions. This model is designed to easily integrate and merge information from other (probabilistic) estimations and heuristics. In particular, it handles uncertainty in enemy units' positions as well as their probable tech tree. We claim that learning, being it supervised or through reinforcement, adapts to skewed data sources. We evaluated our approach on StarCraft 1 : the parameters are learned on a new (freely available) dataset of game states, deterministically re-created from replays, and the whole model is evaluated for prediction in realistic conditions. It is also the tactical decision-making component of our StarCraft AI competition bot.
- a – CNRS
- 1 : Laboratoire d'Informatique de Grenoble (LIG)
- Université Joseph Fourier - Grenoble I – Institut Polytechnique de Grenoble - Grenoble Institute of Technology – Université Pierre-Mendès-France - Grenoble II – CNRS : UMR5217
- 2 : Laboratoire de Physiologie de la Perception et de l'Action (LPPA)
- CNRS : UMR7152 – Collège de France
- Domaine : Informatique/Intelligence artificielle
Informatique/Apprentissage - Mots-clés : machine learning – game AI – RTS games – tactics – tactical decision-making – StarCraft – Bayesian modeling
- hal-00752841, version 1
- http://hal.archives-ouvertes.fr/hal-00752841
- oai:hal.archives-ouvertes.fr:hal-00752841
- Contributeur : Gabriel Synnaeve
- Soumis le : Vendredi 16 Novembre 2012, 15:20:15
- Dernière modification le : Vendredi 16 Novembre 2012, 15:45:00
Documents associés
Exporter