World's Best Scientists 2026 revealed!
Jost Tobias Springenberg

Jost Tobias Springenberg

Award Badge
Rising Stars
2025

D-Index & Metrics

Rising Stars

D-Index
38
Citations
21500
World Ranking
709
National Ranking
18

Computer Science

D-Index
39
Citations
20116
World Ranking
9469
National Ranking
468

Research.com Recognitions

  • 2025 - Research.com Rising Stars Award

Overview

Jost Tobias Springenberg is affiliated with the University of Freiburg in Germany. The primary field of study for Springenberg is Computer Science, with a focus on several subfields including Artificial Intelligence, Computational Theory and Mathematics, Computer Vision and Pattern Recognition, Management Science and Operations Research, as well as Control and Systems Engineering.

Springenberg's research topics cover a range of areas within these fields. The main topics of work include:

  • Reinforcement Learning in Robotics
  • Adaptive Dynamic Programming Control
  • Adversarial Robustness in Machine Learning
  • Robot Manipulation and Learning
  • Multimodal Machine Learning Applications
  • Natural Language Processing Techniques
  • Evolutionary Algorithms and Applications

The scientist has contributed to various research papers, primarily published in recognized venues such as arXiv (Cornell University) and the 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Recent papers include:

  • "Critic Regularized Regression," 2020, arXiv (Cornell University)
  • "A Generalist Agent," 2022, arXiv (Cornell University)
  • "Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning," 2020, arXiv (Cornell University)
  • "Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics," 2020, arXiv (Cornell University)

Springenberg frequently collaborates with a group of co-authors, including:

  • Martin Riedmiller
  • Nicolas Heess
  • Abbas Abdolmaleki
  • Thomas Lampe
  • Roland Hafner

This collaboration pattern suggests engagement with other researchers who have contributed widely to artificial intelligence and robotics domains. The corpus of work demonstrates repeated exploration of reinforcement learning methodologies aimed at robotic applications, as well as theoretical aspects related to dynamic programming and machine learning robustness.

Best Publications

  • Striving for Simplicity: The All Convolutional Net

    Jost Tobias Springenberg;Alexey Dosovitskiy;Thomas Brox;Martin A. Riedmiller

  • Deep learning with convolutional neural networks for EEG decoding and visualization.

    Robin Tibor Schirrmeister;Jost Tobias Springenberg;Lukas Dominique Josef Fiederer;Martin Glasstetter

  • Auto-sklearn: Efficient and Robust Automated Machine Learning

    Matthias Feurer;Aaron Klein;Katharina Eggensperger;Jost Tobias Springenberg

  • Efficient and robust automated machine learning

    Matthias Feurer;Aaron Klein;Katharina Eggensperger;Jost Tobias Springenberg

  • Discriminative Unsupervised Feature Learning with Convolutional Neural Networks

    Alexey Dosovitskiy;Jost Tobias Springenberg;Martin Riedmiller;Thomas Brox

  • Learning to generate chairs with convolutional neural networks

    Alexey Dosovitskiy;Jost Tobias Springenberg;Thomas Brox

  • Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks

    Alexey Dosovitskiy;Philipp Fischer;Jost Tobias Springenberg;Martin Riedmiller

  • Multimodal deep learning for robust RGB-D object recognition

    Andreas Eitel;Jost Tobias Springenberg;Luciano Spinello;Martin Riedmiller

  • Embed to control: a locally Linear Latent dynamics model for control from raw images

    Manuel Watter;Jost Tobias Springenberg;Joschka Boedecker;Martin Riedmiller

  • Speeding up automatic hyperparameter optimization of deep neural networks by extrapolation of learning curves

    Tobias Domhan;Jost Tobias Springenberg;Frank Hutter

  • A Generalist Agent

    Unknown

  • Initializing bayesian hyperparameter optimization via meta-learning

    Matthias Feurer;Jost Tobias Springenberg;Frank Hutter

  • Graph Networks as Learnable Physics Engines for Inference and Control

    Alvaro Sanchez-Gonzalez;Nicolas Heess;Jost Tobias Springenberg;Josh Merel

  • Bayesian optimization with robust Bayesian neural networks

    Jost Tobias Springenberg;Aaron Klein;Stefan Falkner;Frank Hutter

  • Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks

    Jost Tobias Springenberg

  • Learning by Playing - Solving Sparse Reward Tasks from Scratch

    Martin A. Riedmiller;Roland Hafner;Thomas Lampe;Michael Neunert

  • Learning to Generate Chairs, Tables and Cars with Convolutional Networks

    Alexey Dosovitskiy;Jost Tobias Springenberg;Maxim Tatarchenko;Thomas Brox

  • Maximum a Posteriori Policy Optimisation

    Abbas Abdolmaleki;Jost Tobias Springenberg;Yuval Tassa;Rémi Munos

  • Deep reinforcement learning with successor features for navigation across similar environments

    Jingwei Zhang;Jost Tobias Springenberg;Joschka Boedecker;Wolfram Burgard

  • Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks

    Jost Tobias Springenberg

  • Learning an Embedding Space for Transferable Robot Skills

    Karol Hausman;Jost Tobias Springenberg;Ziyu Wang;Nicolas Heess

  • Critic Regularized Regression

    Ziyu Wang;Alexander Novikov;Konrad Zolna;Jost Tobias Springenberg

  • Keep Doing What Worked: Behavior Modelling Priors for Offline Reinforcement Learning

    Noah Siegel;Jost Tobias Springenberg;Felix Berkenkamp;Abbas Abdolmaleki

Frequent Co-Authors

Martin Riedmiller
Martin Riedmiller DeepMind (United Kingdom)
Nicolas Heess
Nicolas Heess DeepMind (United Kingdom)
Frank Hutter
Frank Hutter University of Freiburg
Alexey Dosovitskiy
Alexey Dosovitskiy Google (United States)
Thomas Brox
Thomas Brox University of Freiburg
Wolfram Burgard
Wolfram Burgard University of Technology Nuremberg
Raia Hadsell
Raia Hadsell DeepMind (United Kingdom)
Francesco Nori
Francesco Nori DeepMind (United Kingdom)
Yuval Tassa
Yuval Tassa Google (United States)
Jonas Buchli
Jonas Buchli DeepMind (United Kingdom)

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Pursuing a Computer Science degree in the USA opens doors to a wide range of career pathways. Many students consider supplementing their skills with related disciplines or advanced credentials, often through flexible online programs. For professionals aiming for leadership roles, an online executive mba can add crucial business and management expertise atop a technical background.

If you’re interested in data organization or digital information management, a master in library science offers strong career opportunities, especially in academic and corporate environments. Additionally, students seeking a cost-effective way to advance their qualifications can explore an affordable master degree online in related fields such as data science, cybersecurity, or information technology.

For those aspiring to top executive positions or academic roles, a doctorate in leadership online can be an excellent way to build strategic and organizational expertise. These online pathways offer flexibility and can complement a core background in computer science for a holistic and future-ready career.

Best Scientists Citing Jost Tobias Springenberg

Trending Scientists