Advertisement

Adaptive Learning in Games: Defining Profiles of Competitor Players

  • Tiago PintoEmail author
  • Zita Vale
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 217)

Abstract

Artificial Intelligence has been applied to dynamic games for many years. The ultimate goal is creating responses in virtual entities that display human-like reasoning in the definition of their behaviors. However, virtual entities that can be mistaken for real persons are yet very far from being fully achieved. This paper presents an adaptive learning based methodology for the definition of players’ profiles, with the purpose of supporting decisions of virtual entities. The proposed methodology is based on reinforcement learning algorithms, which are responsible for choosing, along the time, with the gathering of experience, the most appropriate from a set of different learning approaches. These learning approaches have very distinct natures, from mathematical to artificial intelligence and data analysis methodologies, so that the methodology is prepared for very distinct situations. This way it is equipped with a variety of tools that individually can be useful for each encountered situation. The proposed methodology is tested firstly on two simpler computer versus human player games: the rock-paper-scissors game, and a penalty-shootout simulation. Finally, the methodology is applied to the definition of action profiles of electricity market players; players that compete in a dynamic game-wise environment, in which the main goal is the achievement of the highest possible profits in the market.

Keywords

Adaptive Learning Artificial Intelligence Player Profiles 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dietterich, T.: Bridging the gap between specification and implementation. IEEE Expert 6(2), 80–82 (1991)CrossRefGoogle Scholar
  2. 2.
    Simon, H.: Administrative Decision Making. IEEE Engineering Management Review 1(1), 60–66 (1973)CrossRefGoogle Scholar
  3. 3.
    Praça, I., et al.: MASCEM: A Multi-Agent System that Simulates Competitive Electricity Markets. IEEE Intelligent Systems, Special Issue on Agents and Markets 18(6), 54–60 (2003)Google Scholar
  4. 4.
    Vale, Z., Pinto, T., Praça, I., Morais, H.: MASCEM - Electricity markets simulation with strategically acting players. IEEE Intelligent Systems. Special Issue on AI in Power Systems and Energy Markets 26(2) (2011)Google Scholar
  5. 5.
    Meeus, L., et al.: Development of the Internal Electricity Market in Europe. The Electricity Journal 18(6), 25–35 (2005)CrossRefGoogle Scholar
  6. 6.
    OMIE – Operador del Mercado Iberico de Energia website, http://www.omie.es/ (acessed on January 2013)
  7. 7.
    Amjady, N., et al.: Day-ahead electricity price forecasting by modified relief algorithm and hybrid neural network. IET Generation, Transmission & Distribution 4(3), 432–444 (2010)CrossRefGoogle Scholar
  8. 8.
    Erev, I., Roth, A.: Predicting how people play games with unique, mixed-strategy equilibria. American Economic Review 88, 848–881 (1998)Google Scholar
  9. 9.
    Korb, K., Nicholson, A.: Bayesian Artificial Intelligence. Chapman & Hall/CRC (2003)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  1. 1.GECAD – Knowledge Engineering and Decision-Support Research Center, Institute of EngineeringPolitechnic of Porto (ISEP/IPP)PortoPortugal

Personalised recommendations