Showing papers by "Julian Togelius published in 2021"

A Fast and efficient stochastic opposition-based learning for differential evolution in numerical optimization

Abstract: A fast and efficient stochastic opposition-based learning (OBL) variant is proposed in this paper. OBL is a machine learning concept to accelerate the convergence of soft computing algorithms, which consists of simultaneously calculating an original solution and its opposite. Recently, a stochastic OBL variant called BetaCOBL was proposed, which is capable of controlling the degree of opposite solutions, preserving useful information held by original solutions, and preventing the waste of fitness evaluations. While it has shown outstanding performance compared to several state-of-the-art OBL variants, the high computational cost of BetaCOBL may hinder it from cost-sensitive optimization problems. Also, as it assumes that the decision variables of a given problem are independent, BetaCOBL may be ineffective for optimizing inseparable problems. In this paper, we propose an improved BetaCOBL that mitigates all the limitations. The proposed algorithm called iBetaCOBL reduces the computational cost from O(NP2 · D) to O(NP · D) (NP and D stand for population size and a dimension, respectively) using a linear time diversity measure. Also, the proposed algorithm preserves strongly dependent variables that are adjacent to each other using multiple exponential crossover. We used differential evolution (DE) variants to evaluate the performance of the proposed algorithm. The results of the performance evaluations on a set of 58 test functions show the excellent performance of iBetaCOBL compared to ten state-of-the-art OBL variants, including BetaCOBL.

Deep learning for procedural content generation

Abstract: Procedural content generation in video games has a long history. Existing procedural content generation methods, such as search-based, solver-based, rule-based and grammar-based methods have been applied to various content types such as levels, maps, character models, and textures. A research field centered on content generation in games has existed for more than a decade. More recently, deep learning has powered a remarkable range of inventions in content production, which are applicable to games. While some cutting-edge deep learning methods are applied on their own, others are applied in combination with more traditional methods, or in an interactive setting. This article surveys the various deep learning methods that have been applied to generate game content directly or indirectly, discusses deep learning methods that could be used for content generation purposes but are rarely used today, and envisages some limitations and potential future directions of deep learning for procedural content generation.

Mixed-Initiative Level Design with RL Brush

Abstract: This paper introduces RL Brush, a level-editing tool for tile-based games designed for mixed-initiative co-creation. The tool uses reinforcement-learning-based models to augment manual human level-design through the addition of AI-generated suggestions. Here, we apply RL Brush to designing levels for the classic puzzle game Sokoban. We put the tool online and tested it in 39 different sessions. The results show that users using the AI suggestions stay around longer and their created levels on average are more playable and more complex than without.

Self-referential quality diversity through differential MAP-Elites

Abstract: Differential MAP-Elites is a novel algorithm that combines the illumination capacity of CVT-MAP-Elites with the continuous-space optimization capacity of Differential Evolution. The algorithm is motivated by observations that illumination algorithms, and quality-diversity algorithms in general, offer qualitatively new capabilities and applications for evolutionary computation yet are in their original versions relatively unsophisticated optimizers. The basic Differential MAP-Elites algorithm, introduced for the first time here, is relatively simple in that it simply combines the operators from Differential Evolution with the map structure of CVT-MAP-Elites. Experiments based on 25 numerical optimization problems suggest that Differential MAP-Elites clearly outperforms CVT-MAP-Elites, finding better-quality and more diverse solutions.

Illuminating Diverse Neural Cellular Automata for Level Generation

Abstract: We present a method of generating a collection of neural cellular automata (NCA) to design video game levels. While NCAs have so far only been trained via supervised learning, we present a quality diversity (QD) approach to generating a collection of NCA level generators. By framing the problem as a QD problem, our approach can train diverse level generators, whose output levels vary based on aesthetic or functional criteria. To efficiently generate NCAs, we train generators via Covariance Matrix Adaptation MAP-Elites (CMA-ME), a quality diversity algorithm which specializes in continuous search spaces. We apply our new method to generate level generators for several 2D tile-based games: a maze game, Sokoban, and Zelda. Our results show that CMA-ME can generate small NCAs that are diverse yet capable, often satisfying complex solvability criteria for deterministic agents. We compare against a Compositional Pattern-Producing Network (CPPN) baseline trained to produce diverse collections of generators and show that the NCA representation yields a better exploration of level-space.

Impressions of the GDMC AI Settlement Generation Challenge in Minecraft.

Abstract: The GDMC AI settlement generation challenge is a PCG competition about producing an algorithm that can create an "interesting" Minecraft settlement for a given map. This paper contains a collection of written experiences with this competition, by participants, judges, organizers and advisors. We asked people to reflect both on the artifacts themselves, and on the competition in general. The aim of this paper is to offer a shareable and edited collection of experiences and qualitative feedback - which seem to contain a lot of insights on PCG and computational creativity, but would otherwise be lost once the output of the competition is reduced to scalar performance values. We reflect upon some organizational issues for AI competitions, and discuss the future of the GDMC competition.

Learning Controllable Content Generators.

Abstract: It has recently been shown that reinforcement learning can be used to train generators capable of producing high-quality game levels, with quality defined in terms of some user-specified heuristic. To ensure that these generators' output is sufficiently diverse (that is, not amounting to the reproduction of a single optimal level configuration), the generation process is constrained such that the initial seed results in some variance in the generator's output. However, this results in a loss of control over the generated content for the human user. We propose to train generators capable of producing controllably diverse output, by making them "goal-aware." To this end, we add conditional inputs representing how close a generator is to some heuristic, and also modify the reward mechanism to incorporate that value. Testing on multiple domains, we show that the resulting level generators are capable of exploring the space of possible levels in a targeted, controllable manner, producing levels of comparable quality as their goal-unaware counterparts, that are diverse along designer-specified dimensions.

Greedy Scheduling: A Neural Network Method to Reduce Task Failure in Software Crowdsourcing.

Abstract: Context: Highly dynamic and competitive crowdsourcing software development (CSD) marketplaces may experience task failure due to unforeseen reasons, such as increased competition over shared supplier resources, or uncertainty associated with a dynamic worker supply. Existing analysis reveals an average task failure ratio of 15.7\% in software crowdsourcing markets. Goal: The objective of this study is to provide a task scheduling recommendation model for software crowdsourcing platforms in order to improve the success and efficiency of software crowdsourcing. Method: We propose a task scheduling method based on neural networks, and develop a system that can predict and analyze task failure probability upon arrival. More specifically, the model uses a range of input variables, including the number of open tasks in the platform, the average task similarity between arriving tasks and open tasks, the winner's monetary prize, and task duration, to predict the probability of task failure on the planned arrival date and two surplus days. This prediction will offer the recommended day associated with the lowest task failure probability to post the task. The proposed model is based on the workflow and data of Topcoder, one of the primary software crowdsourcing platforms. Results: We present a model that suggests the best recommended arrival dates for any task in the project with surplus of two days per task in the project. The model on average provided 4\% lower failure ratio per project.

Physics-informed attention-based neural network for solving non-linear partial differential equations.

Abstract: Physics-Informed Neural Networks (PINNs) have enabled significant improvements in modelling physical processes described by partial differential equations (PDEs) PINNs are based on simple architectures, and learn the behavior of complex physical systems by optimizing the network parameters to minimize the residual of the underlying PDE Current network architectures share some of the limitations of classical numerical discretization schemes when applied to non-linear differential equations in continuum mechanics A paradigmatic example is the solution of hyperbolic conservation laws that develop highly localized nonlinear shock waves Learning solutions of PDEs with dominant hyperbolic character is a challenge for current PINN approaches, which rely, like most grid-based numerical schemes, on adding artificial dissipation Here, we address the fundamental question of which network architectures are best suited to learn the complex behavior of non-linear PDEs We focus on network architecture rather than on residual regularization Our new methodology, called Physics-Informed Attention-based Neural Networks, (PIANNs), is a combination of recurrent neural networks and attention mechanisms The attention mechanism adapts the behavior of the deep neural network to the non-linear features of the solution, and break the current limitations of PINNs We find that PIANNs effectively capture the shock front in a hyperbolic model problem, and are capable of providing high-quality solutions inside and beyond the training set

Self-Referential Quality Diversity Through Differential Map-Elites

Abstract: Differential MAP-Elites is a novel algorithm that combines the illumination capacity of CVT-MAP-Elites with the continuous-space optimization capacity of Differential Evolution. The algorithm is motivated by observations that illumination algorithms, and quality-diversity algorithms in general, offer qualitatively new capabilities and applications for evolutionary computation yet are in their original versions relatively unsophisticated optimizers. The basic Differential MAP-Elites algorithm, introduced for the first time here, is relatively simple in that it simply combines the operators from Differential Evolution with the map structure of CVT-MAP-Elites. Experiments based on 25 numerical optimization problems suggest that Differential MAP-Elites clearly outperforms CVT-MAP-Elites, finding better-quality and more diverse solutions.

The AI Settlement Generation Challenge in Minecraft: First Year Report

Abstract: This article outlines what we learned from the first year of the AI Settlement Generation Competition in Minecraft, a competition about producing AI programs that can generate interesting settlements in Minecraft for an unseen map. This challenge seeks to focus research into adaptive and holistic procedural content generation. Generating Minecraft towns and villages given existing maps is a suitable task for this, as it requires the generated content to be adaptive, functional, evocative and aesthetic at the same time. Here, we present the results from the first iteration of the competition. We discuss the evaluation methodology, present the different technical approaches by the competitors, and outline the open problems.

An Evolutionary Algorithm for Task Scheduling in Crowdsourced Software Development

Abstract: The complexity of software tasks and the uncertainty of crowd developer behaviors make it challenging to plan crowdsourced software development (CSD) projects. In a competitive crowdsourcing marketplace, competition for shared worker resources from multiple simultaneously open tasks adds another layer of uncertainty to the potential outcomes of software crowdsourcing. These factors lead to the need for supporting CSD managers with automated scheduling to improve the visibility and predictability of crowdsourcing processes and outcomes. To that end, this paper proposes an evolutionary algorithm-based task scheduling method for crowdsourced software development. The proposed evolutionary scheduling method uses a multiobjective genetic algorithm to recommend an optimal task start date. The method uses three fitness functions, based on project duration, task similarity, and task failure prediction, respectively. The task failure fitness function uses a neural network to predict the probability of task failure with respect to a specific task start date. The proposed method then recommends the best tasks start dates for the project as a whole and each individual task so as to achieve the lowest project failure ratio. Experimental results on 4 projects demonstrate that the proposed method has the potential to reduce project duration by a factor of 33-78%.

Game Mechanic Alignment Theory

Abstract: We present a new concept called Game Mechanic Alignment theory as a way to organize game mechanics through the lens of systemic rewards and agential motivations. By disentangling player and systemic influences, mechanics may be better identified for use in an automated tutorial generation system, which could tailor tutorials for a particular playstyle or player. Within, we apply this theory to several well-known games to demonstrate how designers can benefit from it, we describe a methodology for how to estimate “mechanic alignment”, and we apply this methodology on multiple games in the GVGAI framework. We discuss how effectively this estimation captures agential motivations and systemic rewards and how our theory could be used as an alternative way to find mechanics for tutorial generation.

Adversarial Encoder-Multi-Task-Decoder for Multi-Stage Processes

Abstract: In multi-stage processes, decisions occur in an ordered sequence of stages. Early stages usually have more observations with general information (easier/cheaper to collect), while later stages have fewer observations but more specific data. This situation can be represented as a dual funnel structure, in which the sample size decreases from one stage to the other while the information available about each instance increases. Training classifiers in this scenario is challenging since information in the early stages may not contain distinct patterns to learn (underfitting). In contrast, the small sample size in later stages can cause overfitting. We address both cases by introducing a framework that combines adversarial autoencoders (AAE), multitask learning (MTL), and multi-label semi-supervised learning (MLSSL). We improve the decoder of the AAE with MTL so it can jointly reconstruct the original input and use feature nets to predict the features for the next stages. We also introduce a sequence constraint in the output of an MLSSL classifier to guarantee the sequential pattern in the predictions. Using different domains (selection process, medical diagnosis), we show that our approach outperforms other state-of-the-art methods.

Game Mechanic Alignment Theory and Discovery.

Abstract: We present a new concept called Game Mechanic Alignment theory as a way to organize game mechanics through the lens of environmental rewards and intrinsic player motivations. By disentangling player and environmental influences, mechanics may be better identified for use in an automated tutorial generation system, which could tailor tutorials for a particular playstyle or player. Within, we apply this theory to several well-known games to demonstrate how designers can benefit from it, we describe a methodology for how to estimate mechanic alignment, and we apply this methodology on multiple games in the GVGAI framework. We discuss how effectively this estimation captures intrinsic/extrinsic rewards and how our theory could be used as an alternative to critical mechanic discovery methods for tutorial generation.