Divergent search targets unseen or unexpected solutions rather than maximizing an expressly stated objective. For the purposes of my research, I experiment with divergent search for open-ended game content generation as it can break designer fixations and create surprising content.
Abstract: Quality-diversity (QD) algorithms search for a set of good solutions which cover a space as defined by behavior metrics. This simultaneous focus on quality and diversity with explicit metrics sets QD algorithms apart from standard single- and multi-objective evolutionary algorithms, as well as from diversity preservation approaches such as niching. These properties open up new avenues for artificial intelligence in games, in particular for procedural content generation. Creating multiple systematically varying solutions allows new approaches to creative human-AI interaction as well as adaptivity. In the last few years, a handful of applications of QD to procedural content generation and game playing have been proposed; we discuss these and propose challenges for future work.
in Proceedings of the IEEE Conference on Games, 2019. BibTex
Abstract: Quality-diversity algorithms focus on discovering multiple diverse and high-performing solutions. MAP-elites is such an algorithm, as it partitions the solution space into bins and searches for the best solution possible for each bin. In this paper, multi-behavior variants of MAP-Elites are tested where the MAP-Elites grid partitions the solution space based on a certain dimension, while selection is guided by measures of diversity on another dimension. Four divergent search algorithms are tested for this selection process, targeting novelty or surprise or their combination, and their performance on a soft robot evolution task is discussed.
in Proceedings of the Genetic and Evolutionary Computation Conference, 2019. BibTex
Abstract: Quality diversity is a recent family of evolutionary search algorithms which focus on finding several well-performing (quality) yet different (diversity) solutions with the aim to maintain an appropriate balance between divergence and convergence during search. While quality diversity has already delivered promising results in complex problems, the capacity of divergent search variants for quality diversity remains largely unexplored. Inspired by the notion of surprise as an effective driver of divergent search and its orthogonal nature to novelty this paper investigates the impact of the former to quality diversity performance. For that purpose we introduce three new quality diversity algorithms which employ surprise as a diversity measure, either on its own or combined with novelty, and compare their performance against novelty search with local competition, the state of the art quality diversity algorithm. The algorithms are tested in a robot navigation task across 60 highly deceptive mazes. Our findings suggest that allowing surprise and novelty to operate synergistically for divergence and in combination with local competition leads to quality diversity algorithms of significantly higher efficiency, speed and robustness.
in Transactions on Evolutionary Computation, vol. 23, no 4, pp. 603-616, 2019. BibTex
Abstract: Traditional evolutionary algorithms tend to converge to a single good solution, which can limit their chance of discovering more diverse and creative outcomes. Divergent search, on the other hand, aims to counter convergence to local optima by avoiding selection pressure towards the objective. Forms of divergent search such as novelty or surprise search have proven to be beneficial for both the efficiency and the variety of the solutions obtained in deceptive tasks. Importantly for this paper, early results in maze navigation have shown that combining novelty and surprise search yields an even more effective search strategy due to their orthogonal nature. Motivated by the largely unexplored potential of coupling novelty and surprise as a search strategy, in this paper we investigate how fusing the two can affect the evolution of soft robot morphologies. We test the capacity of the combined search strategy against objective, novelty, and surprise search, by comparing their efficiency and robustness, and the variety of robots they evolve. Our key results demonstrate that novelty-surprise search is generally more efficient and robust across eight different resolutions. Further, surprise search explores the space of robot morphologies more broadly than any other algorithm examined.
in Proceedings of the Genetic and Evolutionary Computation Conference, 2018. BibTex
Abstract: Divergent search techniques applied to evolutionary computation, such as novelty search and surprise search, have demonstrated their efficacy in highly deceptive problems compared to traditional objective-based fitness evolutionary processes. While novelty search rewards unseen solutions, surprise search rewards unexpected solutions. As a result these two algorithms perform a different form of search since an expected solution can be novel while an already seen solution can be surprising. As novelty and surprise search have already shown much promise individually, the hypothesis is that an evolutionary process that rewards both novel and surprising solutions will be able to handle deception in a better fashion and lead to more successful solutions faster. In this paper we introduce an algorithm that realises both novelty and surprise search and we compare it against the two algorithms that compose it in a number of robot navigation tasks. The key findings of this paper suggest that coupling novelty and surprise is advantageous compared to each search approach on its own. The introduced algorithm breaks new ground in divergent search as it outperforms both novelty and surprise in terms of efficiency and robustness, and it explores the behavioural space more extensively.
In Proceedings of the Genetic and Evolutionary Computation Conference, 2017. BibTex
Abstract: Divergent search is a recent trend in evolutionary computation that does not reward proximity to the objective of the problem it tries to solve. Traditional evolutionary algorithms tend to converge to a single good solution, using a fitness proportional to the quality of the problem's solution, while divergent algorithms aim to counter convergence by avoiding selection pressure towards the ultimate objective. This paper explores how a recent divergent algorithm, surprise search, can affect the evolution of soft robot morphologies, comparing the performance and the structure of the evolved robots.
In Proceedings of the Genetic and Evolutionary Computation Conference, 2017. BibTex
Abstract: In procedural content generation, it is often desirable to create artifacts which not only fulfill certain playability constraints but are also able to surprise the player with unexpected potential uses. This paper applies a divergent evolutionary search method based on surprise to the constrained problem of generating balanced and efficient sets of weapons for the Unreal Tournament III shooter game. The proposed constrained surprise search algorithm ensures that pairs of weapons are sufficiently balanced and effective while also rewarding unexpected uses of these weapons during game simulations with artificial agents. Results in the paper demonstrate that searching for surprise can create functionally diverse weapons which require new gameplay patterns of weapon use in the game.
in Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG). 2016. BibTex
Abstract: Inspired by the notion of surprise for unconventional discovery in computational creativity, we introduce a general search algorithm we name surprise search. Surprise search is grounded in the divergent search paradigm and is fabricated within the principles of metaheuristic (evolutionary) search. The algorithm mimics the self-surprise cognitive process of creativity and equips computational creators with the ability to search for outcomes that deviate from the algorithm's expected behavior. The predictive model of expected outcomes is based on historical trails of where the search has been and some local information about the search space. We showcase the basic steps of the algorithm via a problem solving (maze navigation) and a generative art task. What distinguishes surprise search from other forms of divergent search, such as the search for novelty, is its ability to diverge not from earlier and seen outcomes but rather from predicted and unseen points in the creative domain considered.
in Proceedings of the International Conference on Computational Creativity. 2016. BibTex
Abstract: Grounded in the divergent search paradigm and inspired by the principle of surprise for unconventional discovery in computational creativity, this paper introduces surprise search as a new method of evolutionary divergent search. Surprise search is tested in two robot navigation tasks and compared against objective-based evolutionary search and novelty search. The key findings of this paper reveal that surprise search is advantageous compared to the other two search processes. It outperforms objective search and it is as efficient as novelty search in both tasks examined. Most importantly, surprise search is, on average, faster and more robust in solving the navigation problem compared to objective and novelty search. Our analysis reveals that surprise search explores the behavioral space more extensively and yields higher population diversity compared to novelty search.
in Proceedings of the Genetic and Evolutionary Computation Conference. ACM, 2016. BibTex
Abstract: This paper describes a method for evolving assets for video games based on their visuals properties. Focusing on assets for a space shooter game, a genotype consisting of turtle commands is transformed into a spaceship image composed of human-authored sprite components. Due to constraints on the final spaceships' plausibility, the paper investigates two-population constrained optimization and constrained novelty search methods. A sample of visual styles is tested, each a combination of visual metrics which primarily evaluate balance and shape complexity. Experiments with constrained optimization of a visual style demonstrate that a visually consistent set of spaceships can be generated, while experiments with constrained novelty search demonstrate that several distinct visual styles can be discovered by exploring along select, or all, visual dimensions.
in Proceedings of Evolutionary and Biologically Inspired Music, Sound, Art and Design (EvoMusArt). Springer, 2016. BibTex
Abstract: In procedural content generation, one is often interested in generating a large number of artifacts that are not only of high quality but also diverse, in terms of gameplay, visual impression or some other criterion. We investigate several search-based approaches to creating good and diverse game content, in particular approaches based on evolution strategies with or without diversity preservation mechanisms, novelty search and random search. The content domain is game levels, more precisely map sketches for strategy games, which are meant to be used as suggestions in the Sentient Sketchbook design tool. Several diversity metrics are possible for this type of content: we investigate tile-based, objective-based and visual impression distance. We find that evolution with diversity preservation mechanisms can produce both good and diverse content, but only when using appropriate distance measures. Reversely, we can draw conclusions about the suitability of these distance measures for the domain from the comparison of diversity preserving versus blind restart evolutionary algorithms.
in Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG), 2014. BibTex
Abstract: Novelty search is a recent algorithm geared towards exploring search spaces without regard to objectives. When the presence of constraints divides a search space into feasible space and infeasible space, interesting implications arise regarding how novelty search explores such spaces. This paper elaborates on the problem of constrained novelty search and proposes two novelty search algorithms which search within both the feasible and the infeasible space. Inspired by the FI-2pop genetic algorithm, both algorithms maintain and evolve two separate populations, one with feasible and one with infeasible individuals, while each population can use its own selection method. The proposed algorithms are applied to the problem of generating diverse but playable game levels, which is representative of the larger problem of procedural game content generation. Results show that the two-population constrained novelty search methods can create, under certain conditions, larger and more diverse sets of feasible game levels than current methods of novelty search, whether constrained or unconstrained. However, the best algorithm is contingent on the particularities of the search space and the genetic operators used. Additionally, the proposed enhancement of offspring boosting is shown to enhance performance in all cases of two-population novelty search.
Evolutionary Computation 21(1), 2015, pp. 101-129. BibTex
Abstract: Novelty search is a recent algorithm geared to explore search spaces without regard to objectives; minimal criteria novelty search is a variant of this algorithm for constrained search spaces. For large search spaces with multiple constraints, however, it is hard to find a set of feasible individuals that is both large and diverse. In this paper, we present two new methods of novelty search for constrained spaces, Feasible-Infeasible Novelty Search and Feasible-Infeasible Dual Novelty Search. Both algorithms keep separate populations of feasible and infeasible individuals, inspired by the FI-2pop genetic algorithm. These algorithms are applied to the problem of creating diverse and feasible game levels, representative of a large class of important problems in procedural content generation for games. Results show that the new algorithms under certain conditions can produce larger and more diverse sets of feasible strategy game maps than existing algorithms. However, the best algorithm is contingent on the particularities of the search space and the genetic operators used. It is also shown that the proposed enhancement of offspring boosting increases performance in all cases.
in Proceedings of the Genetic and Evolutionary Competition Conference, 2013, pp. 343-350. BibTex
Abstract: We introduce DeLeNoX (Deep Learning Novelty Explorer), a system that autonomously creates artifacts in constrained spaces according to its own evolving interestingness criterion. DeLeNoX proceeds in alternating phases of exploration and transformation. In the exploration phases, a version of novelty search augmented with constraint handling searches for maximally diverse artifacts using a given distance function. In the transformation phases, a deep learning autoencoder learns to compress the variation between the found artifacts into a lower-dimensional space. The newly trained encoder is then used as the basis for a new distance function, transforming the criteria for the next exploration phase. In the current paper, we apply DeLeNoX to the creation of spaceships suitable for use in two-dimensional arcade-style computer games, a representative problem in procedural content generation in games. We also situate DeLeNoX in relation to the distinction between exploratory and transformational creativity, and in relation to Schmidhuber's theory of creativity through the drive for compression progress.
in Proceedings of the Fourth International Conference on Computational Creativity, 2013, pp. 56-63. BibTex
Abstract: This paper introduces the Sentient Sketchbook, a tool which supports a designer in the creation of game levels. Using map sketches to alleviate designer effort, the tool automates playability checks and evaluations and visualizes significant gameplay properties. This paper also introduces constrained novelty search via a two-population paradigm for generating, in real-time, alternatives to the author's design and evaluates its potential against current approaches. The paper concludes with a small-scale user study in which industry experts interact with the Sentient Sketchbook to design game levels. Results demonstrate the tool's potential and provide directions for its improvement.
in Proceedings of the 8th Conference on the Foundations of Digital Games, 2013, pp. 213-220. BibTex
Abstract: This paper presents a first step towards a mixed-initiative tool for the creation of game maps. The tool, named Sentient World, allows the designer to draw a rough terrain sketch, adding extra levels of detail through stochastic and gradient search. Novelty search generates a number of dissimilar artificial neural networks that are trained to approximate a designer's sketch and provide maps of higher resolution back to the designer. As the procedurally generated maps are presented to the designer (to accept, reject, or edit) the terrain sketches are iteratively refined into complete high resolution maps which may diverge from initial designer concepts. The tool supports designer creativity while conforming to designer intentions, and maintains constant designer control through the map selection and map editing options. Results obtained on a number of test maps show that novelty search is beneficial for introducing divergent content to the designer without reducing the speed of iterative map refinement.
in Proceedings of Evolutionary and Biologically Inspired Music, Sound, Art and Design (EvoMusArt), vol. 7834, LNCS. Springer, 2013, pp. 180-191. BibTex