Procedural Enemy Generation through Parallel Evolutionary Algorithm

Pereira, Leonardo T.; Viana, Breno M. F.; Toledo, Cláudio Fabiano Motta

doi:10.1109/sbgames54170.2021.00024

Cited by 8 publications

(40 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The research on procedural enemy generation is a recent research area, [7] and this section describes enemy generation methods from research works and industry games regarding any stage of their generative processes and gameplay progress. Table I summarizes our related work findings with the present paper contributions.…”

Section: Related Workmentioning

confidence: 99%

“…Pereira et al [7] presented a Parallel Evolutionary Algorithm (PEA) that generates enemies for an Action-Adventure game. The authors extracted the most common variables from enemies in different Action-Adventure games to build the enemy's genotype.…”

Section: Related Workmentioning

confidence: 99%

“…The enemies may provide different gameplay experiences, which is a relevant aspect for PCG methods [2]. However, PCG methods usually approach enemies by spreading them through a level map [3]- [5], instead of concerning more about how to create themselves [6], [7]. The generation of enemies in terms of attributes and visuals design appeared in some games such as Spore [8], No Man's Sky [9], and Creatures [10].…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…We present in this paper an extension of the enemy generation algorithm introduced by Pereira et al [7]. They introduced a Parallel Evolutionary Algorithm (PAE) to evolve enemies represented by common features of Action-Adventure games [7]. Our approach advances the evolutionary strategy by applying MAP-Elites population to illuminate enemies' space, and we did not evolve the enemies through parallel evolution.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Illuminating the Space of Enemies Through MAP-Elites

Viana¹,

Pereira²,

Toledo³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Action-Adventure games have several challenges to overcome, where the most common are enemies. The enemies' goal is to hinder the players' progression by taking life points, and the way they hinder this progress is distinct for different kinds of enemies. In this context, this paper introduces an extended version of an evolutionary approach for procedurally generating enemies that target the enemy's difficulty as the goal. Our approach advances the enemy generation research by incorporating a MAP-Elites population to generate diverse enemies without losing quality. The computational experiment showed the method converged most enemies in the MAP-Elites in less than a second for most cases. Besides, we experimented with players who played an Action-Adventure game prototype with enemies we generated. This experiment showed that the players enjoyed most levels they played, and we successfully created enemies perceived as easy, medium, or hard to face.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%