Controllable procedural map generation via multiobjective evolution

Abstract

This paper shows how multiobjective evolutionary algorithms can be used to procedurally generate complete and playable maps for real-time strategy (RTS) games. We devise heuristic objective functions that measure properties of maps that impact important aspects of gameplay experience. To show the generality of our approach, we design two different evolvable map representations, one for an imaginary generic strategy game based on heightmaps, and one for the classic RTS game StarCraft. The effect of combining tuples or triples of the objective functions are investigated in systematic experiments, in particular which of the objectives are partially conflicting. A selection of generated maps are visually evaluated by a population of skilled StarCraft players, confirming that most of our objectives 123Genet Program Evolvable Mach (2013) 14:245-277 DOI 10.1007 correspond to perceived gameplay qualities. Our method could be used to completely automate in-game controlled map generation, enabling player-adaptive games, or as a design support tool for human designers.

Extensible Multi-domain Generation of Virtual Worlds using Blackboards

“…the work by Kelly). Alternative approaches to multi-domain content generation include data flow systems (Silva et al, 2015;Ganster and Klein, 2007), combining procedural models into a meta-procedural model (Gurin et al, 2016a;Gurin et al, 2016b;Grosbellet et al, 2015;Genevaux et al, 2015), declarative modelling (Smelik et al, 2010;Smelik et al, 2011), answer set programming (Smith and Mateas, 2011) and evolutionary algorithms (Togelius et al, 2013b). Silva augments generative grammars by representing them as a data flow graph.…”

Evolving missions to create game spaces

“…Level generation has only increased in scale and commercial appeal in recent years with games such as Minecraft (Mojang 2011) and No Man's Sky (Hello Games 2016) embracing it as a major selling point. Academic interest in level generation is similarly extensive, with levels for first person shooters [4], puzzle games [2], sidescrolling platformers [8], strategy games [9] and many other game genres being generated using a diverse set of techniques.…”

“…The family of search-based PCG [1] methods attempt to gradually improve a level by applying local changes; most often, artificial evolution is used and the local changes take the form of mutation of tiles in a grid-based map or recombination of the layouts of two parents to create offspring that combine the features of both parents. In search-based PCG, it is common to select the most promising parents to create the next batch of results (generation) based on a quantifiable objective function which evaluates how appropriate a game level is: examples include the length of its paths [9], the combat duration between artificial agents [4] or the distribution of its treasures [5].…”

Automatic Camera Control: A Dynamic Multi-Objective Perspective

“…Constraints can be added in a straightforward way into the algorithm, we follow the approach of a modified selection scheme as utilized in [20]: search points within infeasible regions get a penalty that resembles the distance to the next feasible region. During the selection phase, individuals that carry the highest penalties are always removed first, disregarding the quality of their other objective values.…”