Evolving Multimodal Behavior With Modular Neural Networks in Ms. Pac-Man

This is an Accepted Manuscript of an article published by ACM. Schrum, J., & Miikkulainen, R. (2014). Evolving Multimodal Behavior with Modular Neural Networks in Ms. Pac-Man. In Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation (pp. 325–332). New York, NY, USA: ACM. https://doi.org/10.1145/2576768.2598234

Schrum, Jacob

Miikkulainen, Risto

2016-12-13

2016-12-13

2014

Schrum, J., & Miikkulainen, R. (2014). Evolving Multimodal Behavior with Modular Neural Networks in Ms. Pac-Man. In Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation (pp. 325–332). New York, NY, USA: ACM. https://doi.org/10.1145/2576768.2598234

https://collections.southwestern.edu/s/suscholar/item/230

Ms. Pac-Man is a challenging video game in which multiple modes of behavior are required to succeed: Ms. Pac-Man must escape ghosts when they are threats, and catch them when they are edible, in addition to eating all pills in each level. Past approaches to learning behavior in Ms. Pac-Man have treated the game as a single task to be learned using monolithic policy representations. In contrast, this paper uses a framework called Modular Multiobjective NEAT to evolve modular neural networks. Each module defines a separate policy; evolution discovers these policies and when to use them. The number of modules can be fixed or learned using a new version of a genetic operator, called Module Mutation, which duplicates an existing module that can then evolve to take on a distinct behavioral identity. Both the fixed modular networks and Module Mutation networks outperform traditional monolithic networks. More interestingly, the best modular networks dedicate modules to critical behaviors that do not follow the customary division of the game into chasing edible and escaping threatening ghosts.

English

ACM

Neural networks

Algorithmic game theory and mechanism design

Evolving multimodal behavior

Article