Due to the increasing complexity of video game environments, automated testing via reinforcement learning agents has gained significance in production environments. This study explores the effectiveness of various observation encoding techniques on agents in navigating complex 3D game environments. The primary challenge addressed is the increasing difficulty of manually testing and navigating expansive and intricate game worlds. The research evaluates how different observation encodings influence agents’ training efficiency and navigation success across several environments. However, the study indicates that there is no universal encoding solution, with performance varying significantly depending on the environment. Conclusively, we suggest future research avenues, including the exploration of basic obstacle learning, imitation learning, parameter optimization, and the investigation of new observation mechanisms. This research provides insights into optimizing agent performance in 3D game development, highlighting the need for further study in observation encoding techniques.

The goal of music segmentation is to identify boundaries between parts of music pieces which are perceived as entities. Segment boundaries often go along with a change in musical properties including instrumentation, key, and tempo (or a combination thereof). One can consider different types (or classes) of boundaries according to these musical properties. In contrast to existing datasets with missing specifications of changing properties for annotated boundaries, we have created a set of artificial music tracks with precise annotations for boundaries of different types. This allows for a profound analysis and interpretation of annotated and predicted boundaries and a more exhaustive comparison of different segmentation algorithms. For this scenario, we formulate a novel multi-objective optimisation task that identifies boundaries of only a specific type. The optimisation is conducted by means of evolutionary multi-objective feature selection and a novelty-based segmentation approach. Furthermore, we provide lists of audio features from non-dominated fronts which most significantly contribute to the estimation of given boundaries (the first objective) and most significantly reduce the performance of the prediction of other boundaries (the second objective).

AMUSE (Advanced MUSic Explorer) was created 2006 as an open-source Java framework for various music information retrieval tasks like feature extraction, feature processing, classification, and evaluation. In contrast to toolboxes which focus on individual MIR-related algorithms, it is possible with AMUSE, for instance, to extract features with Librosa, process them based on events estimated by MIRtoolbox, classify with WEKA or Keras, and validate the models with own classification performance measures. We present several substantial contributions to AMUSE since its first presentation at ISMIR 2010. They include the annotation editor for single and multiple tracks, the support of multi-label and multi-class classification, and new plugins which operate with Keras, Librosa, and Sonic Annotator. Other integrated methods are the structural complexity processing, chord vector feature, aggregation of features around estimated onset events, and evaluation of time event extractors. Further advancements are a more flexible feature extraction with different parameters like frame sizes, possibility to integrate additional tasks beyond algorithms related to supervised classification, marking of features which can be ignored for a classification task, extension of algorithm parameters with external code (e.g., a structure of a Keras neural net), etc.

The concept of structural complexity describes the temporal progress of feature values on different time scales. We apply it to audio features with the goal to classify music files into genres using k-Nearest Neighbors and Random Forest. We use a publicly available data set of 1550 music tracks which are labeled as belonging to one of six different genres (or to none of them). The classification models are trained with the help of eight feature sets that describe different musical aspects (chords, harmony, instruments, timbre, etc.) in order to find out which features are best suited to predict these genres using the structural complexity. We apply evolutionary multi-objective feature selection to measure individual contributions of different structural complexity features for each genre to feature sets with the smallest classification errors. We also introduce a new feature chord vector which is shown to perform significantly better on genre classification with the structural complexity method than the chord features used in a previous work. The statistical analysis of time scales and features leads to several recommendations for the setup of feature processing based on structural complexity.

We propose a novel approach to extract audio features based on evolutionary approximation of instrumental texture in polyphonic audio recordings. A population of mixtures of samples from 51 instruments with 165 individual instrument bodies or playing styles is evolved with the help of musically meaningful genetic operators to produce chords which are as similar as possible to unknown signals. Our algorithm allows for a simultaneous approximation of all onsets/chords from a given audio track. The fitness function is designed to retain mixtures which are not directly comparable because they approximate different segments of a track like intro or verse. Another advantage is that no labelled signals are required to learn supervised models for instrument prediction, and the sample database can be easily extended with further instruments. Although the multilabel classification performance of instrument recognition still has room to be improved, the derived instrumental and pitch statistics are comparable to the best selected semantic features from a large set of 566 descriptors including not only instrument and pitch statistics, but also chord, harmony, structure, temporal, dynamics, emotional, vocal, and further characteristics, even outperforming them for a half of tested music categories.

Feature selection is an important prerequisite for music classification which in turn is becoming more and more ubiquitous since entering the digital music age. Automated classification into genres or even personal categories is currently envisioned even for standard mobile devices. However, classifiers often fail to work well with all available features, and simple greedy methods often fail to select good feature sets, making feature selection for music classification a natural field of application for evolutionary approaches in general, and multi-objective evolutionary algorithms in particular. In this work, we study the potential of applying such a multi-objective evolutionary optimization algorithm for feature selection with different objective sets. The result is promising, thus calling for deeper investigations of this approach.

Music classification is a complex problem which has gained high relevance for organizing large music collections. Different parameters concerning feature extraction, selection, processing and classification have a strong impact on the categorization quality. Since it is very difficult to design a deterministic approach which provides the efficient parameter tuning, we haven chosen a heuristic approach. In our work we apply and compare different evolution strategies for the optimization of feature selection and consolidation using three pre-defined personal user categories. Concepts of local search operators with domain-specific knowledge and self-adaptation are examined. Several suggestions based on an empirical study are discussed and ideas for future work are given.