Vanessa Volz
YOU?
Author Swipe
View article: Comparing Methods for Uncertainty Estimation of Paraganglioma Growth Predictions
Comparing Methods for Uncertainty Estimation of Paraganglioma Growth Predictions Open
Background: Paragangliomas of the head and neck are rare, benign and indolent to slow-growing tumors. Not all tumors require immediate active intervention, and surveillance is a viable management strategy in a large proportion of cases. Tr…
View article: Not All the Same: Understanding and Informing Similarity Estimation in Tile-Based Video Games
Not All the Same: Understanding and Informing Similarity Estimation in Tile-Based Video Games Open
Similarity estimation is essential for many game AI applications, from the\nprocedural generation of distinct assets to automated exploration with\ngame-playing agents. While similarity metrics often substitute human\nevaluation, their ali…
View article: Tools for Landscape Analysis of Optimisation Problems in Procedural Content Generation for Games
Tools for Landscape Analysis of Optimisation Problems in Procedural Content Generation for Games Open
View article: Hybrid Encoding for Generating Large Scale Game Level Patterns With Local Variations
Hybrid Encoding for Generating Large Scale Game Level Patterns With Local Variations Open
Generative Adversarial Networks (GANs) are a powerful indirect genotype-to-phenotype mapping for evolutionary search. Much previous work applying GANs to level generation focuses on fixed-size segments combined into a whole level, but indi…
View article: Hybrid Encoding For Generating Large Scale Game Level Patterns With Local Variations Using a GAN.
Hybrid Encoding For Generating Large Scale Game Level Patterns With Local Variations Using a GAN. Open
Generative Adversarial Networks (GANs) are a powerful indirect genotype-to-phenotype mapping for evolutionary search, but they have limitations. In particular, GAN output does not scale to arbitrary dimensions, and there is no obvious way …
View article: Identifying Properties of Real-World Optimisation Problems through a Questionnaire
Identifying Properties of Real-World Optimisation Problems through a Questionnaire Open
Optimisation algorithms are commonly compared on benchmarks to get insight into performance differences. However, it is not clear how closely benchmarks match the properties of real-world problems because these properties are largely unkno…
View article: Towards Game-Playing AI Benchmarks via Performance Reporting Standards
Towards Game-Playing AI Benchmarks via Performance Reporting Standards Open
While games have been used extensively as milestones to evaluate game-playing AI, there exists no standardised framework for reporting the obtained observations. As a result, it remains difficult to draw general conclusions about the stren…
View article: Capturing Local and Global Patterns in Procedural Content Generation via Machine Learning
Capturing Local and Global Patterns in Procedural Content Generation via Machine Learning Open
Recent procedural content generation via machine learning (PCGML) methods allow learning from existing content to produce similar content automatically. While these approaches are able to generate content for different games (e.g. Super Ma…
View article: Towards realistic optimization benchmarks
Towards realistic optimization benchmarks Open
Benchmarks are a useful tool for empirical performance comparisons. However,\none of the main shortcomings of existing benchmarks is that it remains largely\nunclear how they relate to real-world problems. What does an algorithm's\nperform…
View article: Benchmarking in Optimization: Best Practice and Open Issues
Benchmarking in Optimization: Best Practice and Open Issues Open
This survey compiles ideas and recommendations from more than a dozen researchers with different backgrounds and from different institutes around the world. Promoting best practice in benchmarking is its main goal. The article discusses ei…
View article: CPPN2GAN
CPPN2GAN Open
Generative Adversarial Networks (GANs) are proving to be a powerful indirect genotype-to-phenotype mapping for evolutionary search, but they have limitations. In particular, GAN output does not scale to arbitrary dimensions, and there is n…
View article: Interactive evolution and exploration within latent level-design space of generative adversarial networks
Interactive evolution and exploration within latent level-design space of generative adversarial networks Open
Generative Adversarial Networks (GANs) are an emerging form of indirect encoding. The GAN is trained to induce a latent space on training data, and a real-valued evolutionary algorithm can search that latent space. Such Latent Variable Evo…
View article: Capturing Local and Global Patterns in Procedural Content Generation via\n Machine Learning
Capturing Local and Global Patterns in Procedural Content Generation via\n Machine Learning Open
Recent procedural content generation via machine learning (PCGML) methods\nallow learning from existing content to produce similar content automatically.\nWhile these approaches are able to generate content for different games (e.g.\nSuper…
View article: Towards Realistic Optimization Benchmarks: A Questionnaire on the Properties of Real-World Problems
Towards Realistic Optimization Benchmarks: A Questionnaire on the Properties of Real-World Problems Open
Benchmarks are a useful tool for empirical performance comparisons. However, one of the main shortcomings of existing benchmarks is that it remains largely unclear how they relate to real-world problems. What does an algorithm's performanc…
View article: Interactive Evolution and Exploration Within Latent Level-Design Space\n of Generative Adversarial Networks
Interactive Evolution and Exploration Within Latent Level-Design Space\n of Generative Adversarial Networks Open
Generative Adversarial Networks (GANs) are an emerging form of indirect\nencoding. The GAN is trained to induce a latent space on training data, and a\nreal-valued evolutionary algorithm can search that latent space. Such Latent\nVariable …
View article: Uncertainty Handling in Surrogate Assisted Optimisation of Games
Uncertainty Handling in Surrogate Assisted Optimisation of Games Open
View article: Learning Local Forward Models on Unforgiving Games
Learning Local Forward Models on Unforgiving Games Open
This paper examines learning approaches for forward models based on local cell transition functions. We provide a formal definition of local forward models for which we propose two basic learning approaches. Our analysis is based on the ga…
View article: A Local Approach to Forward Model Learning: Results on the Game of Life Game
A Local Approach to Forward Model Learning: Results on the Game of Life Game Open
This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent. We transform Conway's Game of Life simulation into a single-player game where the objective can be either to preserv…
View article: A Local Approach to Forward Model Learning: Results on the Game of Life\n Game
A Local Approach to Forward Model Learning: Results on the Game of Life\n Game Open
This paper investigates the effect of learning a forward model on the\nperformance of a statistical forward planning agent. We transform Conway's Game\nof Life simulation into a single-player game where the objective can be either\nto pres…
View article: Efficient Evolutionary Methods for Game Agent Optimisation: Model-Based is Best
Efficient Evolutionary Methods for Game Agent Optimisation: Model-Based is Best Open
This paper introduces a simple and fast variant of Planet Wars as a test-bed for statistical planning based Game AI agents, and for noisy hyper-parameter optimisation. Planet Wars is a real-time strategy game with simple rules but complex …
View article: Evolving mario levels in the latent space of a deep convolutional generative adversarial network
Evolving mario levels in the latent space of a deep convolutional generative adversarial network Open
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 fr…
View article: Evolving Mario Levels in the Latent Space of a Deep Convolutional\n Generative Adversarial Network
Evolving Mario Levels in the Latent Space of a Deep Convolutional\n Generative Adversarial Network Open
Generative Adversarial Networks (GANs) are a machine learning approach\ncapable of generating novel example outputs across a space of provided training\nexamples. Procedural Content Generation (PCG) of levels for video games could\nbenefit…
View article: Surrogate-Assisted Partial Order-based Evolutionary Optimisation
Surrogate-Assisted Partial Order-based Evolutionary Optimisation Open
In this paper, we propose a novel approach (SAPEO) to support the survival selection process in multi-objective evolutionary algorithms with surrogate models - it dynamically chooses individuals to evaluate exactly based on the model uncer…
View article: Demonstrating the Feasibility of Automatic Game Balancing
Demonstrating the Feasibility of Automatic Game Balancing Open
Game balancing is an important part of the (computer) game design process, in which designers adapt a game prototype so that the resulting gameplay is as entertaining as possible. In industry, the evaluation of a game is often based on cos…