José Arjona-Medina

Senior Researcher

Jose significantly contributed to Dynatrace Research in the field of Data Science from 2021 until November 2022, focusing on Reinforcement Learning, Deep Learning and Machine Learning.

Authored publications

Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution

Reinforcement Learning algorithms require a large number of samples to solve complex tasks with sparse and delayed rewards. Complex tasks can often be hierarchically decomposed into sub-tasks. A step in the Q-function can be associated with solving a sub-task, where the expectation of the return increases. RUDDER has been introduced to identify the...

Vihang P. Patil, Markus Hofmarcher, Marius-Constantin Dinu, Matthias Dorfer, Patrick M. Blies, Johannes Brandstetter, Jose A. Arjona-Medina, Sepp Hochreiter

| Machine Learning, arXiv:2009.14108 | 2022