Computational Game Theory and Multi-Agent Systems: Strategic Decision-Making in AI Ecosystems
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V3I2P101Keywords:
Multi-agent systems, game theory, reinforcement learning, scalability, coordination, uncertainty, Nash equilibrium, autonomous vehicles, smart grids, online marketplacesAbstract
This paper explores the intersection of computational game theory and multi-agent systems (MAS) in the context of strategic decision-making within artificial intelligence (AI) ecosystems. The integration of these two fields has led to significant advancements in modeling and solving complex strategic interactions among multiple autonomous agents. We begin by providing a comprehensive overview of computational game theory and its key concepts, followed by an in-depth discussion of multi-agent systems and their applications. The paper then delves into the methodologies and algorithms used to model and analyze strategic decision-making in multi-agent environments, including the use of game-theoretic models, reinforcement learning, and evolutionary algorithms. We also present case studies and empirical results to illustrate the practical implications of these approaches. Finally, we discuss the challenges and future directions in this rapidly evolving field.
Downloads
References
[1] Fudenberg, D., & Tirole, J. (1991). Game Theory. MIT Press.
[2] Shoham, Y., & Leyton-Brown, K. (2009). Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations. Cambridge University Press.
[3] Von Neumann, J., & Morgenstern, O. (1944). Theory of Games and Economic Behavior. Princeton University Press.
[4] Littman, M. L. (1994). Markov games as a framework for multi-agent reinforcement learning. In Proceedings of the 11th International Conference on Machine Learning (pp. 157-163).
[5] Bowling, M., & Veloso, M. (2002). Multiagent learning using a variable learning rate. Artificial Intelligence, 136(2), 215-250.
[6] Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Van Den Driessche, G., ... & Hassabis, D. (2016). Mastering the game of Go with deep neural networks and tree search. Nature, 529(7587), 484-489.
[7] Brown, N., & Sandholm, T. (2019). Superhuman AI for heads-up no-limit poker: Libratus beats top professionals. Science, 360(6396), 1243-1248.
[8] Zhang, Y., & Lesser, V. (2005). Multi-agent reinforcement learning in the presence of non-cooperative agents. In Proceedings of the 19th International Joint Conference on Artificial Intelligence (pp. 1523-1528).
[9] Hart, S., & Mas-Colell, A. (2000). A simple adaptive procedure leading to correlated equilibrium. Econometrica, 68(5), 1127-1150.
[10] Nisan, N., Roughgarden, T., Tardos, E., & Vazirani, V. V. (2007). Algorithmic Game Theory. Cambridge University Press.
