Search Results for author: Gerhard Neumann

Found 51 papers, 16 papers with code

Swarm Reinforcement Learning For Adaptive Mesh Refinement

no code implementations3 Apr 2023 Niklas Freymuth, Philipp Dahlinger, Tobias Würth, Luise Kärger, Gerhard Neumann

Adaptive Mesh Refinement (AMR) is crucial for mesh-based simulations, as it allows for dynamically adjusting the resolution of a mesh to trade off computational cost with the simulation accuracy.


Information Maximizing Curriculum: A Curriculum-Based Approach for Training Mixtures of Experts

no code implementations27 Mar 2023 Denis Blessing, Onur Celik, Xiaogang Jia, Moritz Reuss, Maximilian Xiling Li, Rudolf Lioutikov, Gerhard Neumann

We propose a novel curriculum-based approach to learning mixture models in which each component of the MoE is able to select its own subset of the training data for learning.

Grounding Graph Network Simulators using Physical Sensor Observations

1 code implementation23 Feb 2023 Jonas Linkerhägner, Niklas Freymuth, Paul Maria Scheikl, Franziska Mathis-Ullrich, Gerhard Neumann

Our method results in utilization of additional point cloud information to accurately predict stable simulations where existing Graph Network Simulators fail.

Imputation Motion Planning +1

Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors

1 code implementation17 Oct 2022 Niklas Freymuth, Nicolas Schreiber, Philipp Becker, Aleksandar Taranovic, Gerhard Neumann

We find that the geometric descriptors greatly help in generalizing to new task configurations and that combining them with our distribution-matching objective is crucial for representing and reproducing versatile behavior.

Imitation Learning

On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning

1 code implementation17 Oct 2022 Philipp Becker, Gerhard Neumann

We show that RSSMs use a suboptimal inference scheme and that models trained using this inference overestimate the aleatoric uncertainty of the ground truth system.

Model-based Reinforcement Learning reinforcement-learning +1

ProDMPs: A Unified Perspective on Dynamic and Probabilistic Movement Primitives

no code implementations4 Oct 2022 Ge Li, Zeqi Jin, Michael Volpp, Fabian Otto, Rudolf Lioutikov, Gerhard Neumann

MPs can be broadly categorized into two types: (a) dynamics-based approaches that generate smooth trajectories from any initial state, e. g., Dynamic Movement Primitives (DMPs), and (b) probabilistic approaches that capture higher-order statistics of the motion, e. g., Probabilistic Movement Primitives (ProMPs).

Numerical Integration

A Unified Perspective on Natural Gradient Variational Inference with Gaussian Mixture Models

no code implementations23 Sep 2022 Oleg Arenz, Philipp Dahlinger, Zihan Ye, Michael Volpp, Gerhard Neumann

Variational inference with Gaussian mixture models (GMMs) enables learning of highly-tractable yet multi-modal approximations of intractable target distributions.

Variational Inference

FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion

no code implementations22 Sep 2022 Fabian Duffhauss, Ngo Anh Vien, Hanna Ziesche, Gerhard Neumann

Sensor fusion can significantly improve the performance of many computer vision tasks.

MV6D: Multi-View 6D Pose Estimation on RGB-D Frames Using a Deep Point-wise Voting Network

no code implementations1 Aug 2022 Fabian Duffhauss, Tobias Demmler, Gerhard Neumann

We overcome this issue with our novel multi-view 6D pose estimation method called MV6D which accurately predicts the 6D poses of all objects in a cluttered scene based on RGB-D images from multiple perspectives.

6D Pose Estimation Semantic Segmentation

End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Control

no code implementations27 May 2022 Moritz Reuss, Niels van Duijkeren, Robert Krug, Philipp Becker, Vaisakh Shaj, Gerhard Neumann

These models need to precisely capture the robot dynamics, which consist of well-understood components, e. g., rigid body dynamics, and effects that remain challenging to capture, e. g., stick-slip friction and mechanical flexibilities.


Regret-Aware Black-Box Optimization with Natural Gradients, Trust-Regions and Entropy Control

no code implementations24 May 2022 Maximilian Hüttenrauch, Gerhard Neumann

In contrast, stochastic optimizers that are motivated by policy gradients, such as the Model-based Relative Entropy Stochastic Search (MORE) algorithm, directly optimize the expected fitness function without the use of rankings.


Meta-Learning Regrasping Strategies for Physical-Agnostic Objects

no code implementations23 May 2022 Ruijie Chen, Ning Gao, Ngo Anh Vien, Hanna Ziesche, Gerhard Neumann

Grasping inhomogeneous objects, practical use in real-world applications, remains a challenging task due to the unknown physical properties such as mass distribution and coefficient of friction.

Friction Meta-Learning

Reactive Motion Generation on Learned Riemannian Manifolds

no code implementations15 Mar 2022 Hadi Beik-Mohammadi, Søren Hauberg, Georgios Arvanitidis, Gerhard Neumann, Leonel Rozo

We argue that Riemannian manifolds may be learned via human demonstrations in which geodesics are natural motion skills.

What Matters For Meta-Learning Vision Regression Tasks?

2 code implementations CVPR 2022 Ning Gao, Hanna Ziesche, Ngo Anh Vien, Michael Volpp, Gerhard Neumann

To this end, we (i) exhaustively evaluate common meta-learning techniques on these tasks, and (ii) quantitatively analyze the effect of various deep learning techniques commonly used in recent meta-learning algorithms in order to strengthen the generalization capability: data augmentation, domain randomization, task augmentation and meta-regularization.

Contrastive Learning Data Augmentation +4

Specializing Versatile Skill Libraries using Local Mixture of Experts

1 code implementation8 Dec 2021 Onur Celik, Dongzhuoran Zhou, Ge Li, Philipp Becker, Gerhard Neumann

This local and incremental learning results in a modular MoE model of high accuracy and versatility, where both properties can be scaled by adding more components on the fly.

Incremental Learning Reinforcement Learning (RL)

Switching Recurrent Kalman Networks

no code implementations16 Nov 2021 Giao Nguyen-Quynh, Philipp Becker, Chen Qiu, Maja Rudolph, Gerhard Neumann

In addition, driving data can often be multimodal in distribution, meaning that there are distinct predictions that are likely, but averaging can hurt model performance.

Autonomous Driving Time Series Analysis

Versatile Inverse Reinforcement Learning via Cumulative Rewards

no code implementations15 Nov 2021 Niklas Freymuth, Philipp Becker, Gerhard Neumann

Inverse Reinforcement Learning infers a reward function from expert demonstrations, aiming to encode the behavior and intentions of the expert.

reinforcement-learning Reinforcement Learning (RL)

A First-Order Method for Estimating Natural Gradients for Variational Inference with Gaussians and Gaussian Mixture Models

no code implementations29 Sep 2021 Oleg Arenz, Zihan Ye, Philipp Dahlinger, Gerhard Neumann

Effective approaches for Gaussian variational inference are MORE, VOGN, and VON, which are zero-order, first-order, and second-order, respectively.

Variational Inference

A Study on Dense and Sparse (Visual) Rewards in Robot Policy Learning

no code implementations6 Aug 2021 Abdalkarim Mohtasib, Gerhard Neumann, Heriberto Cuayahuitl

We argue that it is crucial to automate the reward learning process so that new skills can be taught to robots by their users.

reinforcement-learning Reinforcement Learning (RL)

Differentiable Robust LQR Layers

no code implementations10 Jun 2021 Ngo Anh Vien, Gerhard Neumann

This paper proposes a differentiable robust LQR layer for reinforcement learning and imitation learning under model uncertainty and stochastic dynamics.

Imitation Learning Inductive Bias

Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty

no code implementations8 Jun 2021 Alireza Ranjbar, Ngo Anh Vien, Hanna Ziesche, Joschka Boedecker, Gerhard Neumann

We propose a new formulation that addresses these limitations by also modifying the feedback signals to the controller with an RL policy and show superior performance of our approach on a contact-rich peg-insertion task under position and orientation uncertainty.

Reinforcement Learning (RL)

Learning Riemannian Manifolds for Geodesic Motion Skills

no code implementations8 Jun 2021 Hadi Beik-Mohammadi, Søren Hauberg, Georgios Arvanitidis, Gerhard Neumann, Leonel Rozo

For robots to work alongside humans and perform in unstructured environments, they must learn new motion skills and adapt them to unseen situations on the fly.

Bayesian Context Aggregation for Neural Processes

no code implementations ICLR 2021 Michael Volpp, Fabian Flürenbrock, Lukas Grossberger, Christian Daniel, Gerhard Neumann

Recently, casting probabilistic regression as a multi-task learning problem in terms of conditional latent variable (CLV) models such as the Neural Process (NP) has shown promising results.

Bayesian Inference Multi-Task Learning +1

Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning

1 code implementation20 Oct 2020 Vaisakh Shaj, Philipp Becker, Dieter Buchler, Harit Pandya, Niels van Duijkeren, C. James Taylor, Marc Hanheide, Gerhard Neumann

We adopt a recent probabilistic recurrent neural network architecture, called Re-current Kalman Networks (RKNs), to model learning by conditioning its transition dynamics on the control actions.


Imitation Learning for Autonomous Trajectory Learning of Robot Arms in Space

no code implementations10 Aug 2020 RB Ashith Shyam, Zhou Hao, Umberto Montanaro, Gerhard Neumann

Since actual hardware implementation of microgravity environment is extremely expensive, the demonstration data for trajectory learning is generated using a model predictive controller (MPC) in a physics based simulator.

Imitation Learning Trajectory Planning

Non-Adversarial Imitation Learning and its Connections to Adversarial Methods

1 code implementation8 Aug 2020 Oleg Arenz, Gerhard Neumann

We also show that our non-adversarial formulation can be used to derive novel algorithms by presenting a method for offline imitation learning that is inspired by the recent ValueDice algorithm, but does not rely on small policy updates for convergence.

Imitation Learning

Expected Information Maximization: Using the I-Projection for Mixture Density Estimation

1 code implementation ICLR 2020 Philipp Becker, Oleg Arenz, Gerhard Neumann

Such behavior is appealing whenever we deal with highly multi-modal data where modelling single modes correctly is more important than covering all the modes.

Density Estimation Traffic Prediction

Trust-Region Variational Inference with Gaussian Mixture Models

no code implementations10 Jul 2019 Oleg Arenz, Mingjun Zhong, Gerhard Neumann

For efficient improvement of the GMM approximation, we derive a lower bound on the corresponding optimization objective enabling us to update the components independently.

Variational Inference

Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces

3 code implementations17 May 2019 Philipp Becker, Harit Pandya, Gregor Gebhardt, Cheng Zhao, James Taylor, Gerhard Neumann

In order to integrate uncertainty estimates into deep time-series modelling, Kalman Filters (KFs) (Kalman et al., 1960) have been integrated with deep learning models, however, such approaches typically rely on approximate inference techniques such as variational inference which makes learning more complex and often less scalable due to approximation errors.

Image Imputation Imputation +3

An Algorithmic Perspective on Imitation Learning

no code implementations16 Nov 2018 Takayuki Osa, Joni Pajarinen, Gerhard Neumann, J. Andrew Bagnell, Pieter Abbeel, Jan Peters

This process of learning from demonstrations, and the study of algorithms to do so, is called imitation learning.

Imitation Learning Learning Theory

Adaptation and Robust Learning of Probabilistic Movement Primitives

1 code implementation31 Aug 2018 Sebastian Gomez-Gonzalez, Gerhard Neumann, Bernhard Schölkopf, Jan Peters

However, to be able to capture variability and correlations between different joints, a probabilistic movement primitive requires the estimation of a larger number of parameters compared to their deterministic counterparts, that focus on modeling only the mean behavior.

Towards Fine Grained Network Flow Prediction

no code implementations20 Aug 2018 Patrick Jahnke, Emmanuel Stapf, Jonas Mieseler, Gerhard Neumann, Patrick Eugster

In this space, into which we transform the input data via a Short-Time Fourier Transform (STFT), the peak structures of flows can be predicted after gleaning their key characteristics, with a Principal Component Analysis (PCA), from past and ongoing flows that stem from the same socket-to-socket connection.

Traffic Prediction

Deep Reinforcement Learning for Swarm Systems

1 code implementation17 Jul 2018 Maximilian Hüttenrauch, Adrian Šošić, Gerhard Neumann

However, concatenation scales poorly to swarm systems with a large number of homogeneous agents as it does not exploit the fundamental properties inherent to these systems: (i) the agents in the swarm are interchangeable and (ii) the exact number of agents in the swarm is irrelevant.

Decision Making reinforcement-learning +1

Local Communication Protocols for Learning Complex Swarm Behaviors with Deep Reinforcement Learning

no code implementations21 Sep 2017 Maximilian Hüttenrauch, Adrian Šošić, Gerhard Neumann

Swarm systems constitute a challenging problem for reinforcement learning (RL) as the algorithm needs to learn decentralized control policies that can cope with limited local sensing and communication abilities of the agents.

reinforcement-learning Reinforcement Learning (RL)

Guided Deep Reinforcement Learning for Swarm Systems

1 code implementation18 Sep 2017 Maximilian Hüttenrauch, Adrian Šošić, Gerhard Neumann

Here, we follow a guided approach where a critic has central access to the global state during learning, which simplifies the policy evaluation problem from a reinforcement learning point of view.

reinforcement-learning Reinforcement Learning (RL)

Local Bayesian Optimization of Motor Skills

no code implementations ICML 2017 Riad Akrour, Dmitry Sorokin, Jan Peters, Gerhard Neumann

Bayesian optimization is renowned for its sample efficiency but its application to higher dimensional tasks is impeded by its focus on global optimization.

Bayesian Optimization Imitation Learning

Catching heuristics are optimal control policies

no code implementations NeurIPS 2016 Boris Belousov, Gerhard Neumann, Constantin A. Rothkopf, Jan R. Peters

In this paper, we show that interception strategies appearing to be heuristics can be understood as computational solutions to the optimal control problem faced by a ball-catching agent acting under uncertainty.

Policy Search with High-Dimensional Context Variables

no code implementations10 Nov 2016 Voot Tangkaratt, Herke van Hoof, Simone Parisi, Gerhard Neumann, Jan Peters, Masashi Sugiyama

A naive application of unsupervised dimensionality reduction methods to the context variables, such as principal component analysis, is insufficient as task-relevant input may be ignored.

Dimensionality Reduction Vocal Bursts Intensity Prediction

Model-Free Trajectory-based Policy Optimization with Monotonic Improvement

no code implementations29 Jun 2016 Riad Akrour, Abbas Abdolmaleki, Hany Abdulsamad, Jan Peters, Gerhard Neumann

In order to show the monotonic improvement of our algorithm, we additionally conduct a theoretical analysis of our policy update scheme to derive a lower bound of the change in policy return between successive iterations.

Probabilistic Movement Primitives

no code implementations NeurIPS 2013 Alexandros Paraschos, Christian Daniel, Jan R. Peters, Gerhard Neumann

In order to use such a trajectory distribution for robot movement control, we analytically derive a stochastic feedback controller which reproduces the given trajectory distribution.

Fitted Q-iteration by Advantage Weighted Regression

no code implementations NeurIPS 2008 Gerhard Neumann, Jan R. Peters

Recently, fitted Q-iteration (FQI) based methods have become more popular due to their increased sample efficiency, a more stable learning process and the higher quality of the resulting policy.


Cannot find the paper you are looking for? You can Submit a new open access paper.