Procedural generation of dungeons’ maps and locked-door missions through an evolutionary algorithm validated with players

Pereira, Leonardo T.; Prado, Paulo Victor de Souza; Lopes, Rafael Miranda; Toledo, Cláudio Fabiano Motta

doi:10.1016/j.eswa.2021.115009

Cited by 13 publications

(14 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So far, the works that generate levels with locked-door missions have applied GG approaches to their solutions. Differently from them, Pereira et al presented a search-based algorithm for dungeon level generation with locked-door missions for Action-Adventure games [18]. The proposed algorithm is the base for the approach introduced in this paper.…”

Section: Workmentioning

confidence: 99%

“…According to van der Linden et al, dungeons are labyrinth environments composed of challenges, rewards, and puzzles interrelated with the playspace and time, where the former is the physical layout where the game takes place [9,24]. Furthermore, these games present missions, i.e., a set of goals that the player must accomplish [18]. Examples of such a mission are: defeat/kill some enemies, talk to characters, collect some items, collect keys to open locked doors, among others.…”

mentioning

confidence: 99%

“…The present paper approaches the locked-door missions for dungeons, applying PCG by extending the evolutionary algorithm (EA) introduced in Pereira et al [18]. The previous work presented an EA capable of generating dungeon levels with locked-door missions that match the game designer parameters for levels and missions.…”

mentioning

confidence: 99%

“…The previous work presented an EA capable of generating dungeon levels with locked-door missions that match the game designer parameters for levels and missions. Our extended version offers two main contributions from [18] and PDG related works. The first one is to advance from the previous EA by evolving also the enemies distribution through the levels' rooms.…”

mentioning

confidence: 99%

“…Our population has two dimensions and is mapped regarding leniency, as defined by Smith et al [20], and exploration coefficient, similar to the concept defined by Liapis et al [15]. The evolutionary parameters are closer to those used by Pereira et al [18]; however, we added the number of enemies as a parameter, and we replaced the number of generations by time-limit as a stop criterion to ensure most levels converge. Also, besides generating levels to match the entered characteristics, our approach aims to balance the distribution of enemies in the levels and provide more diversity based on leniency and exploration criteria as previously mentioned.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Illuminating the Space of Dungeon Maps, Locked-door Missions and Enemy Placement Through MAP-Elites

Viana¹,

Pereira²,

Toledo³

2022

Preprint

View full text Add to dashboard Cite

Procedural Content Generation (PCG) methods are valuable tools to speed up the game development process. Moreover, PCG may also present in games as features, such as the procedural dungeon generation (PDG) in Moonlighter (Digital Sun, 2018). This paper introduces an extended version of an evolutionary dungeon generator by incorporating a MAP-Elites population. Our dungeon levels are discretized with rooms that may have locked-door missions and enemies within them. We encoded the dungeons through a tree structure to ensure the feasibility of missions. We performed computational and user feedback experiments to evaluate our PDG approach. They show that our approach accurately converges almost the whole MAP-Elite population for most executions. Finally, players' feedback indicates that they enjoyed the generated levels, and they could not indicate an algorithm as a level generator. CCS CONCEPTS• Theory of computation → Evolutionary algorithms; • Computing methodologies → Discrete space search; • Applied computing → Computer games.

show abstract

Section: Workmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations