Search Results for author: Thomas Adler

Found 5 papers, 3 papers with code

History Compression via Language Models in Reinforcement Learning

1 code implementation24 May 2022 Fabian Paischer, Thomas Adler, Vihang Patil, Angela Bitto-Nemling, Markus Holzleitner, Sebastian Lehner, Hamid Eghbal-zadeh, Sepp Hochreiter

In a partially observable Markov decision process (POMDP), an agent typically uses a representation of the past to approximate the underlying MDP.


Quantum Optical Experiments Modeled by Long Short-Term Memory

no code implementations30 Oct 2019 Thomas Adler, Manuel Erhard, Mario Krenn, Johannes Brandstetter, Johannes Kofler, Sepp Hochreiter

In this work, we show that machine learning models can provide significant improvement over random search.

Cannot find the paper you are looking for? You can Submit a new open access paper.