Thomas Schmied

According to our database, Thomas Schmied authored at least 7 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks.

Thomas Schmied, Thomas Adler, Vihang Patil, Maximilian Beck, Korbinian Pöppel, Johannes Brandstetter, Günter Klambauer, Razvan Pascanu, Sepp Hochreiter

CoRR, 2024

One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation.

Fabian Paischer, Lukas Hauzenberger, Thomas Schmied, Benedikt Alkin, Marc Peter Deisenroth, Sepp Hochreiter

CoRR, 2024

Retrieval-Augmented Decision Transformer: External Memory for In-context RL.

Thomas Schmied, Fabian Paischer, Vihang Patil, Markus Hofmarcher, Razvan Pascanu, Sepp Hochreiter

CoRR, 2024

2023

Learning to Modulate pre-trained Models in RL.

Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Reactive Exploration to Cope With Non-Stationarity in Lifelong Reinforcement Learning.

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

Proceedings of the Conference on Lifelong Learning Agents, 2022

2021

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

Dominik Schmidt, Thomas Schmied

CoRR, 2021

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

Thomas Schmied, Diego Didona, Andreas C. Döring, Thomas P. Parnell, Nikolas Ioannou

Proceedings of the EuroMLSys@EuroSys 2021, 2021