Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Ritz, Fabian"'
Autor:
Altmann, Philipp, Schönberger, Julian, Illium, Steffen, Zorn, Maximilian, Ritz, Fabian, Haider, Tom, Burton, Simon, Gabor, Thomas
Emergent effects can arise in multi-agent systems (MAS) where execution is decentralized and reliant on local information. These effects may range from minor deviations in behavior to catastrophic system failures. To formally define these effects, we
Externí odkaz:
http://arxiv.org/abs/2408.04514
Autor:
Altmann, Philipp, Davignon, Céline, Zorn, Maximilian, Ritz, Fabian, Linnhoff-Popien, Claudia, Gabor, Thomas
To enhance the interpretability of Reinforcement Learning (RL), we propose Revealing Evolutionary Action Consequence Trajectories (REACT). In contrast to the prevalent practice of validating RL models based on their optimal behavior learned during tr
Externí odkaz:
http://arxiv.org/abs/2404.03359
Autor:
Altmann, Philipp, Ritz, Fabian, Feuchtinger, Leonard, Nüßlein, Jonas, Linnhoff-Popien, Claudia, Phan, Thomy
The safe application of reinforcement learning (RL) requires generalization from limited training data to unseen scenarios. Yet, fulfilling tasks under changing circumstances is a key challenge in RL. Current state-of-the-art approaches for generaliz
Externí odkaz:
http://arxiv.org/abs/2304.13616
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 introduce an imitation buffer to store beneficial trajectories generated b
Externí odkaz:
http://arxiv.org/abs/2301.07421
Autor:
Phan, Thomy, Ritz, Fabian, Altmann, Philipp, Zorn, Maximilian, Nüßlein, Jonas, Kölle, Michael, Gabor, Thomas, Linnhoff-Popien, Claudia
Stochastic partial observability poses a major challenge for decentralized coordination in multi-agent reinforcement learning but is largely neglected in state-of-the-art research due to a strong focus on state-based centralized training for decentra
Externí odkaz:
http://arxiv.org/abs/2301.01649
Autor:
Ritz, Fabian, Phan, Thomy, Sedlmeier, Andreas, Altmann, Philipp, Wieghardt, Jan, Schmid, Reiner, Sauer, Horst, Klein, Cornel, Linnhoff-Popien, Claudia, Gabor, Thomas
Publikováno v:
ISoLA 2022: Leveraging Applications of Formal Methods, Verification and Validation. Adaptation and Learning. pp 249-265
The development of Machine Learning (ML) models is more than just a special case of software development (SD): ML models acquire properties and fulfill requirements even without direct human interaction in a seemingly uncontrollable manner. Nonethele
Externí odkaz:
http://arxiv.org/abs/2208.05219
Autor:
Ritz, Fabian, Phan, Thomy, Müller, Robert, Gabor, Thomas, Sedlmeier, Andreas, Zeller, Marc, Wieghardt, Jan, Schmid, Reiner, Sauer, Horst, Klein, Cornel, Linnhoff-Popien, Claudia
Publikováno v:
Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, 28-37, 2021
A characteristic of reinforcement learning is the ability to develop unforeseen strategies when solving problems. While such strategies sometimes yield superior performance, they may also result in undesired or even dangerous behavior. In industrial
Externí odkaz:
http://arxiv.org/abs/2012.07949
In this work, we thoroughly evaluate the efficacy of pretrained neural networks as feature extractors for anomalous sound detection. In doing so, we leverage the knowledge that is contained in these neural networks to extract semantically rich featur
Externí odkaz:
http://arxiv.org/abs/2012.06282
Autor:
Müller, Robert, Illium, Steffen, Ritz, Fabian, Schröder, Tobias, Platschek, Christian, Ochs, Jörg, Linnhoff-Popien, Claudia
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 deployment. Based on recordings from seven contact microphones attached to
Externí odkaz:
http://arxiv.org/abs/2012.06280
In industrial applications, the early detection of malfunctioning factory machinery is crucial. In this paper, we consider acoustic malfunction detection via transfer learning. Contrary to the majority of current approaches which are based on deep au
Externí odkaz:
http://arxiv.org/abs/2006.03429