Rogue-Like Games as a Playground for Artificial Intelligence – Evolutionary Approach - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

Rogue-Like Games as a Playground for Artificial Intelligence – Evolutionary Approach

(1) , (1)
1
Vojtech Cerny
  • Function : Author
  • PersonId : 1030231
Filip Dechterenko
  • Function : Author
  • PersonId : 1030232

Abstract

Rogue-likes are difficult computer RPG games set in a procedurally generated environment. Attempts have been made at playing these algorithmically, but few of them succeeded. In this paper, we present a platform for developing artificial intelligence (AI) and creating procedural content generators (PCGs) for a rogue-like game Desktop Dungeons. As an example, we employ evolutionary algorithms to recombine greedy strategies for the game. The resulting AI plays the game better than a hand-designed greedy strategy and similarly well to a mediocre player – winning the game 72% of the time. The platform may be used for additional research leading to improving rogue-like games and general PCGs.
Fichier principal
Vignette du fichier
371182_1_En_20_Chapter.pdf (272.5 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01758437 , version 1 (04-04-2018)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Vojtech Cerny, Filip Dechterenko. Rogue-Like Games as a Playground for Artificial Intelligence – Evolutionary Approach. 14th International Conference on Entertainment Computing (ICEC), Sep 2015, Trondheim, Norway. pp.261-271, ⟨10.1007/978-3-319-24589-8_20⟩. ⟨hal-01758437⟩
97 View
1165 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More