Alert button
Picture for Thomas Schmied

Thomas Schmied

Alert button

Learning to Modulate pre-trained Models in RL

Jun 26, 2023
Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter

Figure 1 for Learning to Modulate pre-trained Models in RL
Figure 2 for Learning to Modulate pre-trained Models in RL
Figure 3 for Learning to Modulate pre-trained Models in RL
Figure 4 for Learning to Modulate pre-trained Models in RL
Viaarxiv icon

Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning

Jul 12, 2022
Christian Steinparz, Thomas Schmied, Fabian Paischer, Marius-Constantin Dinu, Vihang Patil, Angela Bitto-Nemling, Hamid Eghbal-zadeh, Sepp Hochreiter

Figure 1 for Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning
Figure 2 for Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning
Figure 3 for Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning
Figure 4 for Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning
Viaarxiv icon

Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari

Nov 19, 2021
Dominik Schmidt, Thomas Schmied

Figure 1 for Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari
Figure 2 for Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari
Figure 3 for Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari
Figure 4 for Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari
Viaarxiv icon

Towards a General Framework for ML-based Self-tuning Databases

Nov 16, 2020
Thomas Schmied, Diego Didona, Andreas Döring, Thomas Parnell, Nikolas Ioannou

Figure 1 for Towards a General Framework for ML-based Self-tuning Databases
Figure 2 for Towards a General Framework for ML-based Self-tuning Databases
Viaarxiv icon