1 code implementation • NeurIPS 2023 • Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter
That is, the performance on the pre-training tasks deteriorates when fine-tuning on new tasks.
1 code implementation • 12 Jul 2022 • Christian Steinparz, Thomas Schmied, Fabian Paischer, Marius-Constantin Dinu, Vihang Patil, Angela Bitto-Nemling, Hamid Eghbal-zadeh, Sepp Hochreiter
Therefore, exploration strategies and learning methods are required that are capable of tracking the steady domain shifts, and adapting to them.
1 code implementation • 19 Nov 2021 • Dominik Schmidt, Thomas Schmied
This paper's contribution is threefold: We (1) propose an improved version of Rainbow, seeking to drastically reduce Rainbow's data, training time, and compute requirements while maintaining its competitive performance; (2) we empirically demonstrate the effectiveness of our approach through experiments on the Arcade Learning Environment, and (3) we conduct a number of ablation studies to investigate the effect of the individual proposed modifications.
no code implementations • 16 Nov 2020 • Thomas Schmied, Diego Didona, Andreas Döring, Thomas Parnell, Nikolas Ioannou
Machine learning (ML) methods have recently emerged as an effective way to perform automated parameter tuning of databases.