Jost Tobias Springenberg

Martin A. Riedmiller, Jost Tobias Springenberg, Joschka Boedecker, 2014, 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL).

A learned feature descriptor for object recognition in RGB-D data

Martin A. Riedmiller, Jost Tobias Springenberg, Manuel Blum, 2012, 2012 IEEE International Conference on Robotics and Automation.

Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning pdf

Martin A. Riedmiller, Thomas Lampe, Abbas Abdolmaleki, 2020, ICLR.

V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control pdf

H. Francis Song, Martin A. Riedmiller, Abbas Abdolmaleki, 2019, ICLR.

Auto-sklearn: Efficient and Robust Automated Machine Learning

Aaron Klein, Frank Hutter, Jost Tobias Springenberg, 2019, Automated Machine Learning.

Speeding Up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning Curves

Frank Hutter, Jost Tobias Springenberg, Tobias Domhan, 2015, IJCAI.

Relative Entropy Regularized Policy Iteration pdf

Yuval Tassa, Steven Bohez, Martin A. Riedmiller, 2018, ArXiv.

Graph networks as learnable physics engines for inference and control pdf

Raia Hadsell, Martin A. Riedmiller, Jost Tobias Springenberg, 2018, ICML.

Local Search for Policy Iteration in Continuous Control pdf

Jackie Kay, Yuval Tassa, Martin A. Riedmiller, 2020, ArXiv.

Rethinking Exploration for Sample-Efficient Policy Learning

Martin A. Riedmiller, Jost Tobias Springenberg, Martin Riedmiller, 2021, ArXiv.

Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images

Martin A. Riedmiller, Jost Tobias Springenberg, Joschka Boedecker, 2015, NIPS.

Learning to Generate Chairs, Tables and Cars with Convolutional Networks

Thomas Brox, Alexey Dosovitskiy, Maxim Tatarchenko, 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models

Martin A. Riedmiller, Thomas Lampe, Abbas Abdolmaleki, 2019, CoRL.

Compositional Transfer in Hierarchical Reinforcement Learning

Thomas Lampe, Abbas Abdolmaleki, Jost Tobias Springenberg, 2019, RSS 2020.

Simple Sensor Intentions for Exploration pdf

Jost Tobias Springenberg, Martin Riedmiller, Markus Wulfmeier, 2020, ArXiv.

Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks

Thomas Brox, Martin A. Riedmiller, Alexey Dosovitskiy, 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Initializing Bayesian Hyperparameter Optimization via Meta-Learning

Frank Hutter, Jost Tobias Springenberg, Matthias Feurer, 2015, AAAI.

Learning Temporal Coherent Features through Life-Time Sparsity

Martin A. Riedmiller, Jost Tobias Springenberg, 2012, ICONIP.

Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics

Martin A. Riedmiller, Thomas Lampe, Jonas Buchli, 2020, CoRL.

Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup pdf

Murilo F. Martins, Martin A. Riedmiller, Thomas Lampe, 2019, Robotics: Science and Systems.

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

Jost Tobias Springenberg, J. T. Springenberg, 2015, ICLR.

On Multi-objective Policy Optimization as a Tool for Reinforcement Learning pdf

Sandy H. Huang, Raia Hadsell, Martin A. Riedmiller, 2021, ArXiv.

Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes pdf

Raia Hadsell, Martin A. Riedmiller, Claudio Fantacci, 2021, CoRL.

Evaluating model-based planning and planner amortization for continuous control pdf

Yuval Tassa, Alessandro Davide Ialongo, Martin A. Riedmiller, 2021, ICLR.

Collect & Infer - a fresh look at data-efficient Reinforcement Learning

Martin A. Riedmiller, Jost Tobias Springenberg, Nicolas Heess, 2021, CoRL.

Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning

Martin A. Riedmiller, Kyunghyun Cho, Abbas Abdolmaleki, 2021, 2101.09458.

Extrapolating Learning Curves of Deep Neural Networks

Jost Tobias Springenberg, F. Hutter, Tobias Domhan, 2014 .

Machine Learning on Massively Parallel Architectures-a case study

Jost Tobias Springenberg, S. Lange, 2012 .

Compositional Transfer in Hierarchical Reinforcement Learning

Martin A. Riedmiller, Jost Tobias Springenberg, N. Heess, 2019, Robotics: Science and Systems.

Critic Regularized Regression

Nando de Freitas, Jost Tobias Springenberg, Scott E. Reed, 2020, NeurIPS.

Supplementary material for : Initializing Bayesian Hyperparameter Optimization via Meta-Learning

Jost Tobias Springenberg, F. Hutter, Matthias Feurer, 2015 .

Revisiting Gaussian mixture critics in off-policy reinforcement learning: a sample-based approach

Matthew W. Hoffman, Martin A. Riedmiller, Jost Tobias Springenberg, 2022, ArXiv.

On the Applicability of Unsupervised Feature Learning for Object Recognition in RGB-D Data

Martin A. Riedmiller, Jost Tobias Springenberg, Martin Riedmiller, 2011 .

Bayesian Neural Networks for Predicting Learning Curves

Aaron Klein, Frank Hutter, Jost Tobias Springenberg, 2016 .

Training Generative Adversarial Networks by Solving Ordinary Differential Equations pdf

Pushmeet Kohli, Jeff Donahue, Jost Tobias Springenberg, 2020, NeurIPS.

A Generalist Agent

Sergio Gomez Colmenarejo, Jost Tobias Springenberg, Ashley D. Edwards, 2022, ArXiv.

How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation

Jost Tobias Springenberg, Alex X. Lee, T. Lampe, 2022, 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

A Generalist Agent

Sergio Gomez Colmenarejo, Jost Tobias Springenberg, Ashley D. Edwards, 2022, ArXiv.

Striving for Simplicity: The All Convolutional Net

Martin A. Riedmiller, Jost Tobias Springenberg, T. Brox, 2014, ICLR.