Követés
Thomas Schmied
Thomas Schmied
PhD Student, Institute for Machine Learning, Johannes Kepler University Linz
E-mail megerősítve itt: ml.jku.at
Cím
Hivatkozott rá
Hivatkozott rá
Év
Reactive exploration to cope with non-stationarity in lifelong reinforcement learning
CA Steinparz, T Schmied, F Paischer, MC Dinu, VP Patil, A Bitto-Nemling, ...
Conference on Lifelong Learning Agents, 441-469, 2022
172022
Fast and data-efficient training of rainbow: an experimental study on atari
D Schmidt, T Schmied
Deep Reinforcement Learning Workshop NeurIPS 2021, 2021
142021
Towards a general framework for ml-based self-tuning databases
T Schmied, D Didona, A Döring, T Parnell, N Ioannou
Proceedings of the 1st Workshop on Machine Learning and Systems, 24-30, 2021
132021
Learning to Modulate pre-trained Models in RL
T Schmied, M Hofmarcher, F Paischer, R Pascanu, S Hochreiter
Advances in Neural Information Processing Systems, 2024
122024
Retrieval-augmented decision transformer: External memory for in-context rl
T Schmied, F Paischer, V Patil, M Hofmarcher, R Pascanu, S Hochreiter
arXiv preprint arXiv:2410.07071, 2024
62024
InfODist: Online distillation with Informative rewards improves generalization in Curriculum Learning
R Siripurapu, VP Patil, K Schweighofer, MC Dinu, T Schmied, LEF Diez, ...
Deep Reinforcement Learning Workshop NeurIPS 2022, 2022
32022
One initialization to rule them all: Fine-tuning via explained variance adaptation
F Paischer, L Hauzenberger, T Schmied, B Alkin, MP Deisenroth, ...
arXiv preprint arXiv:2410.07170, 2024
22024
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
T Schmied, T Adler, V Patil, M Beck, K Pöppel, J Brandstetter, ...
arXiv preprint arXiv:2410.22391, 2024
12024
Self-supervision, data augmentation and online fine-tuning for offline RL
T Schmied
Wien, 2022
12022
Controllable Network Data Balancing with GANs
F Meghdouri, T Schmied, T Gärtner, T Zseby
NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications, 2021
12021
Efficient Reinforcement Learning via Self-supervised learning and Model-based methods
T Schmied, M Thiessen
Challenges of Real-World Reinforcement Learning NeurIPS 2020 Workshop, 2020
2020
A rendszer jelenleg nem tudja elvégezni a műveletet. Próbálkozzon újra később.
Cikkek 1–11