Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964201809> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2964201809 abstract "Generative Adversarial Networks (GANs) are a machine learning approach capable of generating novel example outputs across a space of provided training examples. Procedural Content Generation (PCG) of levels for video games could benefit from such models, especially for games where there is a pre-existing corpus of levels to emulate. This paper trains a GAN to generate levels for Super Mario Bros using a level from the Video Game Level Corpus. The approach successfully generates a variety of levels similar to one in the original corpus, but is further improved by application of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Specifically, various fitness functions are used to discover levels within the latent space of the GAN that maximize desired properties. Simple static properties are optimized, such as a given distribution of tile types. Additionally, the champion A* agent from the 2009 Mario AI competition is used to assess whether a level is playable, and how many jumping actions are required to beat it. These fitness functions allow for the discovery of levels that exist within the space of examples designed by experts, and also guide the search towards levels that fulfill one or more specified objectives." @default.
- W2964201809 created "2019-07-30" @default.
- W2964201809 creator A5020511097 @default.
- W2964201809 creator A5041698869 @default.
- W2964201809 creator A5055813085 @default.
- W2964201809 creator A5062380176 @default.
- W2964201809 creator A5078279091 @default.
- W2964201809 creator A5079803355 @default.
- W2964201809 date "2018-07-02" @default.
- W2964201809 modified "2023-09-30" @default.
- W2964201809 title "Evolving mario levels in the latent space of a deep convolutional generative adversarial network" @default.
- W2964201809 cites W1572584819 @default.
- W2964201809 cites W1964869099 @default.
- W2964201809 cites W2002558294 @default.
- W2964201809 cites W2031734221 @default.
- W2964201809 cites W2053153219 @default.
- W2964201809 cites W2126105956 @default.
- W2964201809 cites W2138537392 @default.
- W2964201809 cites W2168115594 @default.
- W2964201809 cites W2490603777 @default.
- W2964201809 doi "https://doi.org/10.1145/3205455.3205517" @default.
- W2964201809 hasPublicationYear "2018" @default.
- W2964201809 type Work @default.
- W2964201809 sameAs 2964201809 @default.
- W2964201809 citedByCount "168" @default.
- W2964201809 countsByYear W29642018092017 @default.
- W2964201809 countsByYear W29642018092018 @default.
- W2964201809 countsByYear W29642018092019 @default.
- W2964201809 countsByYear W29642018092020 @default.
- W2964201809 countsByYear W29642018092021 @default.
- W2964201809 countsByYear W29642018092022 @default.
- W2964201809 countsByYear W29642018092023 @default.
- W2964201809 crossrefType "proceedings-article" @default.
- W2964201809 hasAuthorship W2964201809A5020511097 @default.
- W2964201809 hasAuthorship W2964201809A5041698869 @default.
- W2964201809 hasAuthorship W2964201809A5055813085 @default.
- W2964201809 hasAuthorship W2964201809A5062380176 @default.
- W2964201809 hasAuthorship W2964201809A5078279091 @default.
- W2964201809 hasAuthorship W2964201809A5079803355 @default.
- W2964201809 hasBestOaLocation W29642018092 @default.
- W2964201809 hasConcept C105902424 @default.
- W2964201809 hasConcept C111919701 @default.
- W2964201809 hasConcept C119857082 @default.
- W2964201809 hasConcept C154945302 @default.
- W2964201809 hasConcept C17744445 @default.
- W2964201809 hasConcept C199539241 @default.
- W2964201809 hasConcept C205555498 @default.
- W2964201809 hasConcept C207002847 @default.
- W2964201809 hasConcept C2778572836 @default.
- W2964201809 hasConcept C2780465443 @default.
- W2964201809 hasConcept C37736160 @default.
- W2964201809 hasConcept C39890363 @default.
- W2964201809 hasConcept C41008148 @default.
- W2964201809 hasConcept C97541855 @default.
- W2964201809 hasConceptScore W2964201809C105902424 @default.
- W2964201809 hasConceptScore W2964201809C111919701 @default.
- W2964201809 hasConceptScore W2964201809C119857082 @default.
- W2964201809 hasConceptScore W2964201809C154945302 @default.
- W2964201809 hasConceptScore W2964201809C17744445 @default.
- W2964201809 hasConceptScore W2964201809C199539241 @default.
- W2964201809 hasConceptScore W2964201809C205555498 @default.
- W2964201809 hasConceptScore W2964201809C207002847 @default.
- W2964201809 hasConceptScore W2964201809C2778572836 @default.
- W2964201809 hasConceptScore W2964201809C2780465443 @default.
- W2964201809 hasConceptScore W2964201809C37736160 @default.
- W2964201809 hasConceptScore W2964201809C39890363 @default.
- W2964201809 hasConceptScore W2964201809C41008148 @default.
- W2964201809 hasConceptScore W2964201809C97541855 @default.
- W2964201809 hasLocation W29642018091 @default.
- W2964201809 hasLocation W29642018092 @default.
- W2964201809 hasOpenAccess W2964201809 @default.
- W2964201809 hasPrimaryLocation W29642018091 @default.
- W2964201809 hasRelatedWork W2901368259 @default.
- W2964201809 hasRelatedWork W2919013397 @default.
- W2964201809 hasRelatedWork W2964157711 @default.
- W2964201809 hasRelatedWork W2984518291 @default.
- W2964201809 hasRelatedWork W3013360982 @default.
- W2964201809 hasRelatedWork W3156291593 @default.
- W2964201809 hasRelatedWork W3159117918 @default.
- W2964201809 hasRelatedWork W3198184493 @default.
- W2964201809 hasRelatedWork W4319083788 @default.
- W2964201809 hasRelatedWork W4366250584 @default.
- W2964201809 isParatext "false" @default.
- W2964201809 isRetracted "false" @default.
- W2964201809 magId "2964201809" @default.
- W2964201809 workType "article" @default.