Discovering emergent agent behaviour with evolutionary finite state machines
Abstract
In this paper we introduce a novel approach to discovering emergent behaviour in multiagent simulations, using evolutionary finite state machines to model intelligent agents in an adversarial two-player game. Agent behaviour is modelled as a finite set of predetermined states. The logic that leads to transitions between states is evolved to maximise fitness, which is determined through execution in a constructive simulation environment. The resultant evolved finite state machine (E-FSM) is evaluated for two finite state machine implementations, one with states specifically designed to perform a known behaviour and the other with states consisting of generic actions. Our experiments demonstrate that this approach can discover complex emergent behaviours from simple, generic actions, and use these behaviours to achieve a position of tactical superiority in the domain of air combat simulation.
RAS ID
27617
Document Type
Conference Proceeding
Date of Publication
2018
School
School of Science
Copyright
subscription content
Publisher
Springer
Recommended Citation
Masek, M., Lam, C., Benke, L., Kelly, L., & Papasimeon, M. (2018). Discovering emergent agent behaviour with evolutionary finite state machines. DOI: https://doi.org/10.1007/978-3-030-03098-8_2
Comments
Masek, M., Lam, C. P., Benke, L., Kelly, L., & Papasimeon, M. (2018, October). Discovering Emergent Agent Behaviour with Evolutionary Finite State Machines. In International Conference on Principles and Practice of Multi-Agent Systems (pp. 19-34). Springer, Cham. Available here