191 citations · 551 across the 134 of their papers we have counts for
23 papers · 1 filter
Illustration of Barren Plateaus in Quantum Computing
Gerhard Stenzel, Tobias Rohe, Michael Kölle +3
Variational Quantum Circuits (VQCs) have emerged as a promising paradigm for quantum machine learning in the NISQ era. While parameter sharing in VQCs can reduce the parameter spac…
Reinforcement Learning for Parameterized Quantum State Preparation: A Comparative Study
Gerhard Stenzel, Isabella Debelic, Michael Kölle +4
We extend directed quantum circuit synthesis (DQCS) with reinforcement learning from purely discrete gate selection to parameterized quantum state preparation with continuous singl…
Long Range Frequency Tuning for QML
Michael Poppel, Markus Baumann, Sebastian Wölckert +2
Angle-encoded variational quantum circuits admit a truncated Fourier series representation of their output, but approximating functions with maximum frequency using fixe…
Quantum Generator Kernels
Philipp Altmann, Maximilian Mansky, Maximilian Zorn +2
Quantum kernel methods offer significant theoretical benefits by rendering classically inseparable features separable in quantum space. Yet, the practical application of Quantum Ma…
Quantum King-Ring Domination in Chess: A QAOA Approach
Gerhard Stenzel, Michael Kölle, Tobias Rohe +4
The Quantum Approximate Optimization Algorithm (QAOA) is extensively benchmarked on synthetic random instances such as MaxCut, TSP, and SAT problems, but these lack semantic struct…
Surrogate Fitness Metrics for Interpretable Reinforcement Learning
Philipp Altmann, Céline Davignon, Maximilian Zorn +3
We employ an evolutionary optimization framework that perturbs initial states to generate informative and diverse policy demonstrations. A joint surrogate fitness function guides t…
Investigating Parameter-Efficiency of Hybrid QuGANs Based on Geometric Properties of Generated Sea Route Graphs
Tobias Rohe, Florian Burger, Michael Kölle +3
The demand for artificially generated data for the development, training and testing of new algorithms is omnipresent. Quantum computing (QC), does offer the hope that its inherent…
Efficient Quantum One-Class Support Vector Machines for Anomaly Detection Using Randomized Measurements and Variable Subsampling
Michael Kölle, Afrae Ahouzi, Pascal Debus +4
Quantum one-class support vector machines leverage the advantage of quantum kernel methods for semi-supervised anomaly detection. However, their quadratic time complexity with resp…
REACT: Revealing Evolutionary Action Consequence Trajectories for Interpretable Reinforcement Learning
Philipp Altmann, Céline Davignon, Maximilian Zorn +3
To enhance the interpretability of Reinforcement Learning (RL), we propose Revealing Evolutionary Action Consequence Trajectories (REACT). In contrast to the prevalent practice of…
CROP: Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing
Philipp Altmann, Fabian Ritz, Leonard Feuchtinger +3
The safe application of reinforcement learning (RL) requires generalization from limited training data to unseen scenarios. Yet, fulfilling tasks under changing circumstances is a…
DIRECT: Learning from Sparse and Shifting Rewards using Discriminative Reward Co-Training
Philipp Altmann, Thomy Phan, Fabian Ritz +2
We propose discriminative reward co-training (DIRECT) as an extension to deep reinforcement learning algorithms. Building upon the concept of self-imitation learning (SIL), we intr…
Compression of GPS Trajectories using Autoencoders
Michael Kölle, Steffen Illium, Carsten Hahn +3
The ubiquitous availability of mobile devices capable of location tracking led to a significant rise in the collection of GPS data. Several compression methods have been developed…
Empirical Analysis of Limits for Memory Distance in Recurrent Neural Networks
Steffen Illium, Thore Schillman, Robert Müller +2
Common to all different kinds of recurrent neural networks (RNNs) is the intention to model relations between data points through time. When there is no immediate relationship betw…
Case-Based Inverse Reinforcement Learning Using Temporal Coherence
Jonas Nüßlein, Steffen Illium, Robert Müller +2
Providing expert trajectories in the context of Imitation Learning is often expensive and time-consuming. The goal must therefore be to create algorithms which require as little ex…
Black Box Optimization Using QUBO and the Cross Entropy Method
Jonas Nüßlein, Christoph Roch, Thomas Gabor +3
Black-box optimization (BBO) can be used to optimize functions whose analytic form is unknown. A common approach to realising BBO is to learn a surrogate model which approximates t…
Quantifying Multimodality in World Models
Andreas Sedlmeier, Michael Kölle, Robert Müller +2
Model-based Deep Reinforcement Learning (RL) assumes the availability of a model of an environment's underlying transition dynamics. This model can be used to predict future effect…
Acoustic Leak Detection in Water Networks
Robert Müller, Steffen Illium, Fabian Ritz +4
In this work, we present a general procedure for acoustic leak detection in water networks that satisfies multiple real-world constraints such as energy efficiency and ease of depl…
SAT-MARL: Specification Aware Training in Multi-Agent Reinforcement Learning
Fabian Ritz, Thomy Phan, Robert Müller +8
A characteristic of reinforcement learning is the ability to develop unforeseen strategies when solving problems. While such strategies sometimes yield superior performance, they m…
Policy Entropy for Out-of-Distribution Classification
Andreas Sedlmeier, Robert Müller, Steffen Illium +1
One critical prerequisite for the deployment of reinforcement learning systems in the real world is the ability to reliably detect situations on which the agent was not trained. Su…
Uncertainty-Based Out-of-Distribution Classification in Deep Reinforcement Learning
Andreas Sedlmeier, Thomas Gabor, Thomy Phan +2
Robustness to out-of-distribution (OOD) data is an important goal in building reliable machine learning systems. Especially in autonomous systems, wrong predictions for OOD inputs…
Soccer Team Vectors
Robert Müller, Stefan Langer, Fabian Ritz +3
In this work we present STEVE - Soccer TEam VEctors, a principled approach for learning real valued vectors for soccer teams where similar teams are close to each other in the resu…
Uncertainty-Based Out-of-Distribution Detection in Deep Reinforcement Learning
Andreas Sedlmeier, Thomas Gabor, Thomy Phan +2
We consider the problem of detecting out-of-distribution (OOD) samples in deep reinforcement learning. In a value based reinforcement learning setting, we propose to use uncertaint…
Qualitative Assessment of Recurrent Human Motion
Andre Ebert, Michael Till Beck, Andy Mattausch +2
Smartphone applications designed to track human motion in combination with wearable sensors, e.g., during physical exercising, raised huge attention recently. Commonly, they provid…