Models, code, and papers for "Jost Tobias Springenberg":

Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks

Apr 30, 2016
Jost Tobias Springenberg

In this paper we present a method for learning a discriminative classifier from unlabeled or partially labeled data. Our approach is based on an objective function that trades-off mutual information between observed examples and their predicted categorical class distribution, against robustness of the classifier to an adversarial generative model. The resulting algorithm can either be interpreted as a natural generalization of the generative adversarial networks (GAN) framework or as an extension of the regularized information maximization (RIM) framework to robust classification against an optimal adversary. We empirically evaluate our method - which we dub categorical generative adversarial networks (or CatGAN) - on synthetic data as well as on challenging image classification tasks, demonstrating the robustness of the learned classifiers. We further qualitatively assess the fidelity of samples generated by the adversarial generator that is learned alongside the discriminative classifier, and identify links between the CatGAN objective and discriminative clustering algorithms (such as RIM).

  Click for Model/Code and Paper
Improving Deep Neural Networks with Probabilistic Maxout Units

Feb 19, 2014
Jost Tobias Springenberg, Martin Riedmiller

We present a probabilistic variant of the recently introduced maxout unit. The success of deep neural networks utilizing maxout can partly be attributed to favorable performance under dropout, when compared to rectified linear units. It however also depends on the fact that each maxout unit performs a pooling operation over a group of linear transformations and is thus partially invariant to changes in its input. Starting from this observation we ask the question: Can the desirable properties of maxout units be preserved while improving their invariance properties ? We argue that our probabilistic maxout (probout) units successfully achieve this balance. We quantitatively verify this claim and report classification performance matching or exceeding the current state of the art on three challenging image classification benchmarks (CIFAR-10, CIFAR-100 and SVHN).

  Click for Model/Code and Paper
Unsupervised feature learning by augmenting single images

Feb 16, 2014
Alexey Dosovitskiy, Jost Tobias Springenberg, Thomas Brox

When deep learning is applied to visual object recognition, data augmentation is often used to generate additional training data without extra labeling cost. It helps to reduce overfitting and increase the performance of the algorithm. In this paper we investigate if it is possible to use data augmentation as the main component of an unsupervised feature learning architecture. To that end we sample a set of random image patches and declare each of them to be a separate single-image surrogate class. We then extend these trivial one-element classes by applying a variety of transformations to the initial 'seed' patches. Finally we train a convolutional neural network to discriminate between these surrogate classes. The feature representation learned by the network can then be used in various vision tasks. We find that this simple feature learning algorithm is surprisingly successful, achieving competitive classification results on several popular vision datasets (STL-10, CIFAR-10, Caltech-101).

* ICLR 2014 workshop track submission (7 pages, 4 figures, 1 table) 

  Click for Model/Code and Paper
Learning to Generate Chairs, Tables and Cars with Convolutional Networks

Aug 02, 2017
Alexey Dosovitskiy, Jost Tobias Springenberg, Maxim Tatarchenko, Thomas Brox

We train generative 'up-convolutional' neural networks which are able to generate images of objects given object style, viewpoint, and color. We train the networks on rendered 3D models of chairs, tables, and cars. Our experiments show that the networks do not merely learn all images by heart, but rather find a meaningful representation of 3D models allowing them to assess the similarity of different models, interpolate between given views to generate the missing ones, extrapolate views, and invent new objects not present in the training set by recombining training instances, or even two different object classes. Moreover, we show that such generative networks can be used to find correspondences between different objects from the dataset, outperforming existing approaches on this task.

* v4: final PAMI version. New architecture figure 

  Click for Model/Code and Paper
Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments

Jul 23, 2017
Jingwei Zhang, Jost Tobias Springenberg, Joschka Boedecker, Wolfram Burgard

In this paper we consider the problem of robot navigation in simple maze-like environments where the robot has to rely on its onboard sensors to perform the navigation task. In particular, we are interested in solutions to this problem that do not require localization, mapping or planning. Additionally, we require that our solution can quickly adapt to new situations (e.g., changing navigation goals and environments). To meet these criteria we frame this problem as a sequence of related reinforcement learning tasks. We propose a successor feature based deep reinforcement learning algorithm that can learn to transfer knowledge from previously mastered navigation tasks to new problem instances. Our algorithm substantially decreases the required learning time after the first task instance has been solved, which makes it easily adaptable to changing environments. We validate our method in both simulated and real robot experiments with a Robotino and compare it to a set of baseline methods including classical planning-based navigation.

* Camera ready version for IROS 2017 

  Click for Model/Code and Paper
Asynchronous Stochastic Gradient MCMC with Elastic Coupling

Dec 08, 2016
Jost Tobias Springenberg, Aaron Klein, Stefan Falkner, Frank Hutter

We consider parallel asynchronous Markov Chain Monte Carlo (MCMC) sampling for problems where we can leverage (stochastic) gradients to define continuous dynamics which explore the target distribution. We outline a solution strategy for this setting based on stochastic gradient Hamiltonian Monte Carlo sampling (SGHMC) which we alter to include an elastic coupling term that ties together multiple MCMC instances. The proposed strategy turns inherently sequential HMC algorithms into asynchronous parallel versions. First experiments empirically show that the resulting parallel sampler significantly speeds up exploration of the target distribution, when compared to standard SGHMC, and is less prone to the harmful effects of stale gradients than a naive parallelization approach.

  Click for Model/Code and Paper
Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images

Nov 20, 2015
Manuel Watter, Jost Tobias Springenberg, Joschka Boedecker, Martin Riedmiller

We introduce Embed to Control (E2C), a method for model learning and control of non-linear dynamical systems from raw pixel images. E2C consists of a deep generative model, belonging to the family of variational autoencoders, that learns to generate image trajectories from a latent space in which the dynamics is constrained to be locally linear. Our model is derived directly from an optimal control formulation in latent space, supports long-term prediction of image sequences and exhibits strong performance on a variety of complex control problems.

* Final NIPS version 

  Click for Model/Code and Paper
Striving for Simplicity: The All Convolutional Net

Apr 13, 2015
Jost Tobias Springenberg, Alexey Dosovitskiy, Thomas Brox, Martin Riedmiller

Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers. We re-evaluate the state of the art for object recognition from small images with convolutional networks, questioning the necessity of different components in the pipeline. We find that max-pooling can simply be replaced by a convolutional layer with increased stride without loss in accuracy on several image recognition benchmarks. Following this finding -- and building on other recent work for finding simple network structures -- we propose a new architecture that consists solely of convolutional layers and yields competitive or state of the art performance on several object recognition datasets (CIFAR-10, CIFAR-100, ImageNet). To analyze the network we introduce a new variant of the "deconvolution approach" for visualizing features learned by CNNs, which can be applied to a broader range of network structures than existing approaches.

* accepted to ICLR-2015 workshop track; no changes other than style 

  Click for Model/Code and Paper
Self-supervised Learning of Image Embedding for Continuous Control

Jan 03, 2019
Carlos Florensa, Jonas Degrave, Nicolas Heess, Jost Tobias Springenberg, Martin Riedmiller

Operating directly from raw high dimensional sensory inputs like images is still a challenge for robotic control. Recently, Reinforcement Learning methods have been proposed to solve specific tasks end-to-end, from pixels to torques. However, these approaches assume the access to a specified reward which may require specialized instrumentation of the environment. Furthermore, the obtained policy and representations tend to be task specific and may not transfer well. In this work we investigate completely self-supervised learning of a general image embedding and control primitives, based on finding the shortest time to reach any state. We also introduce a new structure for the state-action value function that builds a connection between model-free and model-based methods, and improves the performance of the learning algorithm. We experimentally demonstrate these findings in three simulated robotic tasks.

* Contributed talk at Inference to Control workshop at NeurIPS2018 

  Click for Model/Code and Paper
Multimodal Deep Learning for Robust RGB-D Object Recognition

Aug 18, 2015
Andreas Eitel, Jost Tobias Springenberg, Luciano Spinello, Martin Riedmiller, Wolfram Burgard

Robust object recognition is a crucial ingredient of many, if not all, real-world robotics applications. This paper leverages recent progress on Convolutional Neural Networks (CNNs) and proposes a novel RGB-D architecture for object recognition. Our architecture is composed of two separate CNN processing streams - one for each modality - which are consecutively combined with a late fusion network. We focus on learning with imperfect sensor data, a typical problem in real-world robotics tasks. For accurate learning, we introduce a multi-stage training methodology and two crucial ingredients for handling depth data with CNNs. The first, an effective encoding of depth information for CNNs that enables learning without the need for large depth datasets. The second, a data augmentation scheme for robust learning with depth images by corrupting them with realistic noise patterns. We present state-of-the-art results on the RGB-D object dataset and show recognition in challenging RGB-D real-world noisy settings.

* Final version submitted to IROS'2015, results unchanged, reformulation of some text passages in abstract and introduction 

  Click for Model/Code and Paper
Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks

Jun 19, 2015
Alexey Dosovitskiy, Philipp Fischer, Jost Tobias Springenberg, Martin Riedmiller, Thomas Brox

Deep convolutional networks have proven to be very successful in learning task specific features that allow for unprecedented performance on various computer vision tasks. Training of such networks follows mostly the supervised learning paradigm, where sufficiently many input-output pairs are required for training. Acquisition of large training sets is one of the key challenges, when approaching a new task. In this paper, we aim for generic feature learning and present an approach for training a convolutional network using only unlabeled data. To this end, we train the network to discriminate between a set of surrogate classes. Each surrogate class is formed by applying a variety of transformations to a randomly sampled 'seed' image patch. In contrast to supervised network training, the resulting feature representation is not class specific. It rather provides robustness to the transformations that have been applied during training. This generic feature representation allows for classification results that outperform the state of the art for unsupervised learning on several popular datasets (STL-10, CIFAR-10, Caltech-101, Caltech-256). While such generic features cannot compete with class specific features from supervised training on a classification task, we show that they are advantageous on geometric matching problems, where they also outperform the SIFT descriptor.

* PAMI submission. Includes matching experiments as in arXiv:1405.5769v1. Also includes new network architectures, experiments on Caltech-256, experiment on combining Exemplar-CNN with clustering 

  Click for Model/Code and Paper
Maximum a Posteriori Policy Optimisation

Jun 14, 2018
Abbas Abdolmaleki, Jost Tobias Springenberg, Yuval Tassa, Remi Munos, Nicolas Heess, Martin Riedmiller

We introduce a new algorithm for reinforcement learning called Maximum aposteriori Policy Optimisation (MPO) based on coordinate ascent on a relative entropy objective. We show that several existing methods can directly be related to our derivation. We develop two off-policy algorithms and demonstrate that they are competitive with the state-of-the-art in deep reinforcement learning. In particular, for continuous control, our method outperforms existing methods with respect to sample efficiency, premature convergence and robustness to hyperparameter settings while achieving similar or better final performance.

  Click for Model/Code and Paper
Graph networks as learnable physics engines for inference and control

Jun 04, 2018
Alvaro Sanchez-Gonzalez, Nicolas Heess, Jost Tobias Springenberg, Josh Merel, Martin Riedmiller, Raia Hadsell, Peter Battaglia

Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, or explicitly in a transition model. Here we introduce a new class of learnable models--based on graph networks--which implement an inductive bias for object- and relation-centric representations of complex, dynamical systems. Our results show that as a forward model, our approach supports accurate predictions from real and simulated data, and surprisingly strong and efficient generalization, across eight distinct physical systems which we varied parametrically and structurally. We also found that our inference model can perform system identification. Our models are also differentiable, and support online planning via gradient-based trajectory optimization, as well as offline policy optimization. Our framework offers new opportunities for harnessing and exploiting rich knowledge about the world, and takes a key step toward building machines with more human-like representations of the world.

* ICML 2018 

  Click for Model/Code and Paper
Relative Entropy Regularized Policy Iteration

Dec 05, 2018
Abbas Abdolmaleki, Jost Tobias Springenberg, Jonas Degrave, Steven Bohez, Yuval Tassa, Dan Belov, Nicolas Heess, Martin Riedmiller

We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of three steps: i) policy evaluation by estimating a parametric action-value function; ii) policy improvement via the estimation of a local non-parametric policy; and iii) generalization by fitting a parametric policy. Each step can be implemented in different ways, giving rise to several algorithm variants. Our algorithm draws on connections to existing literature on black-box optimization and 'RL as an inference' and it can be seen either as an extension of the Maximum a Posteriori Policy Optimisation algorithm (MPO) [Abdolmaleki et al., 2018a], or as an extension of Trust Region Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES) [Abdolmaleki et al., 2017b; Hansen et al., 1997] to a policy iteration scheme. Our comparison on 31 continuous control tasks from parkour suite [Heess et al., 2017], DeepMind control suite [Tassa et al., 2018] and OpenAI Gym [Brockman et al., 2016] with diverse properties, limited amount of compute and a single set of hyperparameters, demonstrate the effectiveness of our method and the state of art results. Videos, summarizing results, can be found at .

  Click for Model/Code and Paper
Robust Reinforcement Learning for Continuous Control with Model Misspecification

Jun 18, 2019
Daniel J. Mankowitz, Nir Levine, Rae Jeong, Abbas Abdolmaleki, Jost Tobias Springenberg, Timothy Mann, Todd Hester, Martin Riedmiller

We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifically focus on incorporating robustness into a state-of-the-art continuous control RL algorithm called Maximum a-posteriori Policy Optimization (MPO). We achieve this by learning a policy that optimizes for a worst case, entropy-regularized, expected return objective and derive a corresponding robust entropy-regularized Bellman contraction operator. In addition, we introduce a less conservative, soft-robust, entropy-regularized objective with a corresponding Bellman operator. We show that both, robust and soft-robust policies, outperform their non-robust counterparts in nine Mujoco domains with environment perturbations. Finally, we present multiple investigative experiments that provide a deeper insight into the robustness framework; including an adaptation to another continuous control RL algorithm as well as comparing this approach to domain randomization. Performance videos can be found online at

  Click for Model/Code and Paper
Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models

Oct 09, 2019
Arunkumar Byravan, Jost Tobias Springenberg, Abbas Abdolmaleki, Roland Hafner, Michael Neunert, Thomas Lampe, Noah Siegel, Nicolas Heess, Martin Riedmiller

Humans are masters at quickly learning many complex tasks, relying on an approximate understanding of the dynamics of their environments. In much the same way, we would like our learning agents to quickly adapt to new tasks. In this paper, we explore how model-based Reinforcement Learning (RL) can facilitate transfer to new tasks. We develop an algorithm that learns an action-conditional, predictive model of expected future observations, rewards and values from which a policy can be derived by following the gradient of the estimated value along imagined trajectories. We show how robust policy optimization can be achieved in robot manipulation tasks even with approximate models that are learned directly from vision and proprioception. We evaluate the efficacy of our approach in a transfer learning scenario, re-using previously learned models on tasks with different reward structures and visual distractors, and show a significant improvement in learning speed compared to strong off-policy baselines. Videos with results can be found at

* To appear at the 3rd annual Conference on Robot Learning, Osaka, Japan (CoRL 2019). 24 pages including appendix (main paper - 8 pages) 

  Click for Model/Code and Paper
Regularized Hierarchical Policies for Compositional Transfer in Robotics

Jun 27, 2019
Markus Wulfmeier, Abbas Abdolmaleki, Roland Hafner, Jost Tobias Springenberg, Michael Neunert, Tim Hertweck, Thomas Lampe, Noah Siegel, Nicolas Heess, Martin Riedmiller

The successful application of flexible, general learning algorithms -- such as deep reinforcement learning -- to real-world robotics applications is often limited by their poor data-efficiency. Domains with more than a single dominant task of interest encourage algorithms that share partial solutions across tasks to limit the required experiment time. We develop and investigate simple hierarchical inductive biases -- in the form of structured policies -- as a mechanism for knowledge transfer across tasks in reinforcement learning (RL). To leverage the power of these structured policies we design an RL algorithm that enables stable and fast learning. We demonstrate the success of our method both in simulated robot environments (using locomotion and manipulation domains) as well as real robot experiments, demonstrating substantially better data-efficiency than competitive baselines.

* Preprint. Under review. Addressed typos 

  Click for Model/Code and Paper
Learning by Playing - Solving Sparse Reward Tasks from Scratch

Feb 28, 2018
Martin Riedmiller, Roland Hafner, Thomas Lampe, Michael Neunert, Jonas Degrave, Tom Van de Wiele, Volodymyr Mnih, Nicolas Heess, Jost Tobias Springenberg

We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm in the context of Reinforcement Learning (RL). SAC-X enables learning of complex behaviors - from scratch - in the presence of multiple sparse reward signals. To this end, the agent is equipped with a set of general auxiliary tasks, that it attempts to learn simultaneously via off-policy RL. The key idea behind our method is that active (learned) scheduling and execution of auxiliary policies allows the agent to efficiently explore its environment - enabling it to excel at sparse reward RL. Our experiments in several challenging robotic manipulation settings demonstrate the power of our approach.

* A video of the rich set of learned behaviours can be found at 

  Click for Model/Code and Paper
Deep learning with convolutional neural networks for EEG decoding and visualization

Jun 08, 2018
Robin Tibor Schirrmeister, Jost Tobias Springenberg, Lukas Dominique Josef Fiederer, Martin Glasstetter, Katharina Eggensperger, Michael Tangermann, Frank Hutter, Wolfram Burgard, Tonio Ball

PLEASE READ AND CITE THE REVISED VERSION at Human Brain Mapping: Code available here:

* A revised manuscript (with the new title) has been accepted at Human Brain Mapping, see 

  Click for Model/Code and Paper
V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control

Sep 26, 2019
H. Francis Song, Abbas Abdolmaleki, Jost Tobias Springenberg, Aidan Clark, Hubert Soyer, Jack W. Rae, Seb Noury, Arun Ahuja, Siqi Liu, Dhruva Tirumala, Nicolas Heess, Dan Belov, Martin Riedmiller, Matthew M. Botvinick

Some of the most successful applications of deep reinforcement learning to challenging domains in discrete and continuous control have used policy gradient methods in the on-policy setting. However, policy gradients can suffer from large variance that may limit performance, and in practice require carefully tuned entropy regularization to prevent policy collapse. As an alternative to policy gradient algorithms, we introduce V-MPO, an on-policy adaptation of Maximum a Posteriori Policy Optimization (MPO) that performs policy iteration based on a learned state-value function. We show that V-MPO surpasses previously reported scores for both the Atari-57 and DMLab-30 benchmark suites in the multi-task setting, and does so reliably without importance weighting, entropy regularization, or population-based tuning of hyperparameters. On individual DMLab and Atari levels, the proposed algorithm can achieve scores that are substantially higher than has previously been reported. V-MPO is also applicable to problems with high-dimensional, continuous action spaces, which we demonstrate in the context of learning to control simulated humanoids with 22 degrees of freedom from full state observations and 56 degrees of freedom from pixel observations, as well as example OpenAI Gym tasks where V-MPO achieves substantially higher asymptotic scores than previously reported.

* * equal contribution 

  Click for Model/Code and Paper