Johannes Ackermann

I’m a second-year PhD student at the University of Tokyo, working on Reinforcement Learning, but also broader Machine Learning.

I’m also employed by RIKEN AIP as a part-time researcher and supported by a Japanese government MEXT scholarship.

I recently interned at Preferred Networks and previously worked as a DSP engineer in Huawei’s Munich Research Center, working on applied Machine Learning. Before that, I received my B.Sc. and M.Sc. in Electrical Engineering and Information Technology from the Technical University of Munich in 2018 and 2021.

I wrote my Master’s Thesis about Multi-Task RL in ETH Zurich’s Distributed Computing group.

news

Dec 5, 2022 I presented our work High-Resolution Image Editing via Multi-Stage Blended Diffusion from my internship in PFN at the NeurIPS Machine Learning for Creativity and Design Workshop :tada:
Apr 20, 2022 I posted a blog-entry detailing how I built a Text to Image web app!
Apr 1, 2022 I passed my entrance examination at the Computer Science Department and am now officially a doctoral student in the University of Tokyo!
Sep 1, 2021 Our paper on Unsupervised Task Clustering for Multi-Task Reinforcement Learning was accepted for publication at ECML-PKDD 2021 :tada:

publications

  1. High-Resolution Image Editing via Multi-Stage Blended Diffusion
    Ackermann, Johannes, and Li, Minjun
    In NeurIPS Machine Learning for Creativity and Design Workshop 2022 2022
    PDF
  2. Unsupervised Task Clustering for Multi-Task Reinforcement Learning
    Ackermann, Johannes, Richter, Oliver, and Wattenhofer, Roger
    In ECML-PKDD 2021 2021
    PDF
  3. Convolutional Neural Network Based Blind Estimation of Generalized Mutual Information for Optical Communication
    Ackermann, Johannes, Schädler, Maximilian, and Blümm, Christian
    In European Conference on Optical Communication (ECOC) 2020
    PDF
  4. Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics
    Ackermann, Johannes, Gabler, Volker, Osa, Takayuki, and Sugiyama, Masashi
    In Deep Reinforcement Learning Workshop at NeurIPS 2019
    PDF