Sledovať
Tom Haider
Tom Haider
Fraunhofer IKS
Overená e-mailová adresa na: iks.fraunhofer.de
Názov
Citované v
Citované v
Rok
Out-of-distribution detection for reinforcement learning agents with probabilistic dynamics models
T Haider, K Roscher, F Schmoeller da Roza, S Günnemann
Proceedings of the 2023 International Conference on Autonomous Agents and …, 2023
202023
Domain Shifts in Reinforcement Learning: Identifying Disturbances in Environments.
T Haider, FS Roza, D Eilers, K Roscher, S Günnemann
AISafety@ IJCAI, 2021
152021
Towards anomaly detection in reinforcement learning
R Müller, S Illium, T Phan, T Haider, C Linnhoff-Popien
Proceedings of the 21st International Conference on Autonomous Agents and …, 2022
142022
Human-machine collaboration on data annotation of images by semi-automatic labeling
T Haider, F Michahelles
Proceedings of Mensch und Computer 2021, 552-556, 2021
52021
Emergence in Multi-agent Systems: A Safety Perspective
P Altmann, J Schönberger, S Illium, M Zorn, F Ritz, T Haider, S Burton, ...
International Symposium on Leveraging Applications of Formal Methods, 104-120, 2024
22024
Reinforcement learning with ensemble model predictive safety certification
S Gronauer, T Haider, FS da Roza, K Diepold
arXiv preprint arXiv:2402.04182, 2024
22024
A Comparison of Ambulance Redeployment Systems on Real-World Data
N Strauß, M Berrendorf, T Haider, M Schubert
2022 IEEE International Conference on Data Mining Workshops (ICDMW), 1-8, 2022
22022
Can you trust your agent? The effect of out-of-distribution detection on the safety of reinforcement learning systems
T Haider, K Roscher, B Herd, F Schmoeller Roza, S Burton
Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing, 1569-1578, 2024
12024
Systém momentálne nemôže vykonať operáciu. Skúste to neskôr.
Články 1–8