Abstract
When a predator chases its prey, a mind game ensues, requiring both predator and prey to predict what the other will do next. These elements of uncertainty and opponency are also seen in analyses of real-world tasks and games. For instance, one way to define an optimal solution of a non-cooperative game is to find the Nash equilibrium, a state in which each agent in a game has optimized its strategy given the strategies of others. The Regularized Nash Dynamics (R-NaD) algorithm guarantees that policies will converge to the Nash equilibrium, creating AIs that beat top human players in tasks with hidden information. Our research compares the performance of deep reinforcement learning agents trained with and without R-NaD in a simple hide-and-seek game, aiming to see how well the agents process unknowns in the environment. We then apply explainable AI (XAI) techniques to the trained model to examine the kinds of information that trained policies encode about opponent strategies. We find that policies trained with R-NaD outperform policies trained in regular self-play when there is hidden information. Furthermore, R-NaD policies use their opponent’s past positions to decide which actions to take, more so than regular self-play. These findings yield insights on how animals and artificial agents operate under spatial uncertainty.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7), e0130140 (2015)
Ellis, B.J., Jordan, A.C., Grotuss, J., Csinady, A., Keenan, T., Bjorklund, D.F.: The predator-avoidance effect: an evolved constraint on emerging theory of mind. Evol. Hum. Behav. 35(3), 245–256 (2014)
Knight, I.: So you want to make AI bots? A gentle intro into reinforcement learning. Github (2023). https://github.com/isknight/rl_intro
Krichmar, J.L., Hwu, T., Zou, X., Hylton, T.: Advantage of prediction and mental imagery for goal-directed behaviour in agents and robots. Cogn. Comput. Syst. 1(1), 12–19 (2019)
Montavon, G., Binder, A., Lapuschkin, S., Samek, W., Müller, K.R.: Layer-wise relevance propagation: an overview. In: Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, pp. 193–209 (2019)
Perolat, J., et al.: Mastering the game of stratego with model-free multiagent reinforcement learning. Science 378(6623), 990–996 (2022)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
Acknowledgments
We credit Riot Games for funding this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Disclosure of Interests
We declare that the authors have no competing interests.
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hwu, T., McDonald, C., Haxby, S., Teixeira, F., Knight, I., Wang, A. (2025). The Role of Theory of Mind in Finding Predator-Prey Nash Equilibria. In: Brock, O., Krichmar, J. (eds) From Animals to Animats 17. SAB 2024. Lecture Notes in Computer Science(), vol 14993. Springer, Cham. https://doi.org/10.1007/978-3-031-71533-4_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-71533-4_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-71532-7
Online ISBN: 978-3-031-71533-4
eBook Packages: Computer ScienceComputer Science (R0)