❶ Assessing Software Developers ❷ Algorithm Selection for Optimal Multi-Agent Path Finding

Abstract:

The work presented in the seminar is about an automated machine learning method to evaluate programming skills. Our goal was to create an unbiased and automated method that enables developers evaluation without the need for human interaction. In this seminar, we will discuss the methods that were used to collect the developers as well as to analyze them. We will discuss the results that were acquired as well as the conclusions and the future work that is available from this research.​​

Bio:

The challenge of finding an optimal solution to a multi-agent pathfinding (MAPF) problem has attracted significant academic and industrial interest in recent years. While the problem is NP-Hard, modern optimal MAPF algorithms can scale to solve problems with hundreds of agents. Nevertheless, no single optimal MAPF algorithm dominates all benchmarks problems, and there are no clear, provable, guidelines for when each algorithm should be used. To address this, we present the first successful Algorithm Selection (AS) model for optimal MAPF. We propose two approaches to learning an AS model. The first approach uses a standard supervised learning algorithm with a set of handcrafted MAPF-specific features. The second approach casts a MAPF problem to an image and applies a deep Convolutional Neural Network to classify it. We evaluate both approaches over a large dataset and show that using an AS model to select which algorithm to use for each instance results in solving more problems and in a shorter runtime compared to the state of the art.  

Bio: