papers

Publications (126)

cs.LG2023

MP3: Movement Primitive-Based (Re-)Planning Policy

Fabian Otto, Hongyi Zhou, Onur Celik +3

We introduce a novel deep reinforcement learning (RL) approach called Movement Primitive-based Planning Policy (MP3). By integrating movement primitives (MPs) into the deep RL fram…

cs.LG2023

Grounding Graph Network Simulators using Physical Sensor Observations

Jonas Linkerhägner, Niklas Freymuth, Paul Maria Scheikl +2

Physical simulations that accurately model reality are crucial for many engineering disciplines such as mechanical engineering and robotic motion planning. In recent years, learned…

cs.LG2026

VLA-FAIL: Efficient Task Failure Detection for Finetuned Vision-Language-Action Models

Florian Seligmann, Emiliyan Gospodinov, Enes Ulas Dincer +1

Vision-language-action models (VLAs) achieve state-of-the-art performance on many robotic manipulation tasks, yet they can still behave unpredictably in out-of-distribution scenari…

cs.LG2024

Combining Reconstruction and Contrastive Methods for Multimodal Representations in RL

Philipp Becker, Sebastian Mossburger, Fabian Otto +1

Learning self-supervised representations using reconstruction or contrastive losses improves performance and sample complexity of image-based and multimodal reinforcement learning…

cs.LG2021

Switching Recurrent Kalman Networks

Giao Nguyen-Quynh, Philipp Becker, Chen Qiu +2

Forecasting driving behavior or other sensor measurements is an essential component of autonomous driving systems. Often real-world multivariate time series data is hard to model b…

cs.LG2023

Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios

Vaisakh Shaj, Dieter Buchler, Rohit Sonker +2

Recurrent State-space models (RSSMs) are highly expressive models for learning patterns in time series data and system identification. However, these models assume that the dynamic…

cs.RO2020

Imitation Learning for Autonomous Trajectory Learning of Robot Arms in Space

RB Ashith Shyam, Zhou Hao, Umberto Montanaro +1

This work adds on to the on-going efforts to provide more autonomy to space robots. Here the concept of programming by demonstration or imitation learning is used for trajectory pl…

cs.RO2025

Beyond Task Performance: Human Experience in Human-Robot Collaboration

Sean Kille, Jan Heinrich Robens, Philipp Dahlinger +8

Human interaction experience plays a crucial role in the effectiveness of human-machine collaboration, especially as interactions in future systems progress towards tighter physica…

cs.RO2021

Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty

Alireza Ranjbar, Ngo Anh Vien, Hanna Ziesche +2

While classic control theory offers state of the art solutions in many problem scenarios, it is often desired to improve beyond the structure of such solutions and surpass their li…

cs.LG2024

PointPatchRL -- Masked Reconstruction Improves Reinforcement Learning on Point Clouds

Balázs Gyenes, Nikolai Franke, Philipp Becker +1

Perceiving the environment via cameras is crucial for Reinforcement Learning (RL) in robotics. While images are a convenient form of representation, they often complicate extractin…

cs.RO2021

Navigate-and-Seek: a Robotics Framework for People Localization in Agricultural Environments

Riccardo Polvara, Francesco Del Duchetto, Gerhard Neumann +1

The agricultural domain offers a working environment where many human laborers are nowadays employed to maintain or harvest crops, with huge potential for productivity gains throug…

cs.RO2024

MuTT: A Multimodal Trajectory Transformer for Robot Skills

Claudius Kienle, Benjamin Alt, Onur Celik +4

High-level robot skills represent an increasingly popular paradigm in robot programming. However, configuring the skills' parameters for a specific task remains a manual and time-c…

cs.LG2026

PAWS: Preference Learning with Advantage-Weighted Segments

Aleksandar Taranovic, Onur Celik, Niklas Freymuth +6

Preference-based reinforcement learning (PbRL) learns policies from human trajectory-level comparisons, avoiding explicit reward design and expert demonstrations. Existing methods…

cs.RO2024

BMP: Bridging the Gap between B-Spline and Movement Primitives

Weiran Liao, Ge Li, Hongyi Zhou +2

This work introduces B-spline Movement Primitives (BMPs), a new Movement Primitive (MP) variant that leverages B-splines for motion representation. B-splines are a well-known conce…

cs.LG2022

Specializing Versatile Skill Libraries using Local Mixture of Experts

Onur Celik, Dongzhuoran Zhou, Ge Li +2

A long-cherished vision in robotics is to equip robots with skills that match the versatility and precision of humans. For example, when playing table tennis, a robot should be cap…

cs.LG2024

Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling

Denis Blessing, Xiaogang Jia, Johannes Esslinger +2

Monte Carlo methods, Variational Inference, and their combinations play a pivotal role in sampling from intractable probability distributions. However, current studies lack a unifi…

cs.LG2026

Trust-Region Diffusion Policies for Massively Parallel On-Policy RL

Huy Le, Onur Celik, Denis Blessing +6

Reinforcement learning with massively parallel simulations has become a standard framework for developing robust, deployable policies; however, most existing approaches still rely…

cs.RO2023

Reactive Motion Generation on Learned Riemannian Manifolds

Hadi Beik-Mohammadi, Søren Hauberg, Georgios Arvanitidis +2

In recent decades, advancements in motion learning have enabled robots to acquire new skills and adapt to unseen conditions in both structured and unstructured environments. In pra…

cs.LG2025

MaNGO - Adaptable Graph Network Simulators via Meta-Learning

Philipp Dahlinger, Tai Hoang, Denis Blessing +2

Accurately simulating physics is crucial across scientific domains, with applications spanning from robotics to materials science. While traditional mesh-based simulations are prec…

cs.LG2024

Variational Distillation of Diffusion Policies into Mixture of Experts

Hongyi Zhou, Denis Blessing, Ge Li +4

This work introduces Variational Diffusion Distillation (VDD), a novel method that distills denoising diffusion policies into Mixtures of Experts (MoE) through variational inferenc…

cs.LG2025

AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction

Niklas Freymuth, Tobias Würth, Nicolas Schreiber +9

The cost and accuracy of simulating complex physical systems using the Finite Element Method (FEM) scales with the resolution of the underlying mesh. Adaptive meshes improve comput…

cs.LG2026

TROLL: Trust Regions improve Reinforcement Learning for Large Language Models

Philipp Becker, Niklas Freymuth, Serge Thilges +2

Reinforcement Learning (RL) with PPO-like clip objectives has become the standard choice for reward-based fine-tuning of large language models (LLMs). Although recent work has expl…

cs.LG2021

Differentiable Trust Region Layers for Deep Reinforcement Learning

Fabian Otto, Philipp Becker, Ngo Anh Vien +2

Trust region methods are a popular tool in reinforcement learning as they yield robust policy updates in continuous and discrete action spaces. However, enforcing such trust region…

cs.MA2017

Guided Deep Reinforcement Learning for Swarm Systems

Maximilian Hüttenrauch, Adrian Šošić, Gerhard Neumann

In this paper, we investigate how to learn to control a group of cooperative agents with limited sensing capabilities such as robot swarms. The agents have only very basic sensor c…

cs.RO2023

DMFC-GraspNet: Differentiable Multi-Fingered Robotic Grasp Generation in Cluttered Scenes

Philipp Blättner, Johannes Brand, Gerhard Neumann +1

Robotic grasping is a fundamental skill required for object manipulation in robotics. Multi-fingered robotic hands, which mimic the structure of the human hand, can potentially per…

cs.LG2019

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

Philipp Becker, Harit Pandya, Gregor Gebhardt +3

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, suc…

cs.MA2023

Swarm Reinforcement Learning For Adaptive Mesh Refinement

Niklas Freymuth, Philipp Dahlinger, Tobias Würth +3

Adaptive Mesh Refinement (AMR) enhances the Finite Element Method, an important technique for simulating complex problems in engineering, by dynamically refining mesh regions, enab…

cs.LG2025

TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning

Ge Li, Dong Tian, Hongyi Zhou +3

This work introduces Transformer-based Off-Policy Episodic Reinforcement Learning (TOP-ERL), a novel algorithm that enables off-policy updates in the ERL framework. In ERL, policie…

cs.LG2020

Non-Adversarial Imitation Learning and its Connections to Adversarial Methods

Oleg Arenz, Gerhard Neumann

Many modern methods for imitation learning and inverse reinforcement learning, such as GAIL or AIRL, are based on an adversarial formulation. These methods apply GANs to match the…

cs.LG2026

Towards Near-Real-Time Telemetry-Aware Routing with Neural Routing Algorithms

Andreas Boltres, Niklas Freymuth, Benjamin Schichtholz +2

Routing algorithms are crucial for efficient computer network operations, and in many settings they must be able to react to traffic bursts within milliseconds. Live telemetry data…

cs.LG2023

Curriculum-Based Imitation of Versatile Skills

Maximilian Xiling Li, Onur Celik, Philipp Becker +3

Learning skills by imitation is a promising concept for the intuitive teaching of robots. A common way to learn such skills is to learn a parametric model by maximizing the likelih…

cs.LG2024

Learning Sub-Second Routing Optimization in Computer Networks requires Packet-Level Dynamics

Andreas Boltres, Niklas Freymuth, Patrick Jahnke +2

Finding efficient routes for data packets is an essential task in computer networking. The optimal routes depend greatly on the current network topology, state and traffic demand,…

cs.RO2026

PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning

Xiaogang Jia, Qian Wang, Anrui Wang +12

Robotic manipulation systems benefit from complementary sensing modalities, where each provides unique environmental information. Point clouds capture detailed geometric structure,…

cs.RO2020

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

Vaisakh Shaj, Philipp Becker, Dieter Buchler +5

Estimating accurate forward and inverse dynamics models is a crucial component of model-based control for sophisticated robots such as robots driven by hydraulics, artificial muscl…

cs.LG2026

Adaptive Swarm Mesh Refinement using Deep Reinforcement Learning with Local Rewards

Niklas Freymuth, Philipp Dahlinger, Tobias Würth +3

Simulating physical systems is essential in engineering, but analytical solutions are limited to straightforward problems. Consequently, numerical methods like the Finite Element M…

cs.LG2025

Underdamped Diffusion Bridges with Applications to Sampling

Denis Blessing, Julius Berner, Lorenz Richter +1

We provide a general framework for learning diffusion bridges that transport prior to target distributions. It includes existing diffusion models for generative modeling, but also…

cs.LG2024

Physics-informed MeshGraphNets (PI-MGNs): Neural finite element solvers for non-stationary and nonlinear simulations on arbitrary meshes

Tobias Würth, Niklas Freymuth, Clemens Zimmerling +2

Engineering components must meet increasing technological demands in ever shorter development cycles. To face these challenges, a holistic approach is essential that allows for the…

cs.LG2018

Model-Free Trajectory-based Policy Optimization with Monotonic Improvement

Riad Akrour, Abbas Abdolmaleki, Hany Abdulsamad +2

Many of the recent trajectory optimization algorithms alternate between linear approximation of the system dynamics around the mean trajectory and conservative policy update. One w…

cs.LG2025

Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics

Tobias Würth, Niklas Freymuth, Gerhard Neumann +1

Graph-based learned simulators have emerged as a promising approach for simulating physical systems on unstructured meshes, offering speed and generalization across diverse geometr…

cs.LG2024

MaIL: Improving Imitation Learning with Mamba

Xiaogang Jia, Qian Wang, Atalay Donat +7

This work presents Mamba Imitation Learning (MaIL), a novel imitation learning (IL) architecture that provides an alternative to state-of-the-art (SoTA) Transformer-based policies.…

cs.RO2024

Neural Contractive Dynamical Systems

Hadi Beik-Mohammadi, Søren Hauberg, Georgios Arvanitidis +3

Stability guarantees are crucial when ensuring a fully autonomous robot does not take undesirable or potentially harmful actions. Unfortunately, global stability guarantees are har…

cs.RO2021

Probabilistic approach to physical object disentangling

Joni Pajarinen, Oleg Arenz, Jan Peters +1

Physically disentangling entangled objects from each other is a problem encountered in waste segregation or in any task that requires disassembly of structures. Often there are no…

cs.LG2025

DIME:Diffusion-Based Maximum Entropy Reinforcement Learning

Onur Celik, Zechu Li, Denis Blessing +5

Maximum entropy reinforcement learning (MaxEnt-RL) has become the standard approach to RL due to its beneficial exploration properties. Traditionally, policies are parameterized us…

cs.CV2022

What Matters For Meta-Learning Vision Regression Tasks?

Ning Gao, Hanna Ziesche, Ngo Anh Vien +2

Meta-learning is widely used in few-shot classification and function regression due to its ability to quickly adapt to unseen tasks. However, it has not yet been well explored on r…

cs.RO2026

Robot-DIFT: Correspondence-Sensitive Diffusion Features for Contact-Rich Robot Manipulation

Yu Deng, Yufeng Jin, Xiaogang Jia +3

Robot manipulation often fails in the final millimeters: a policy may recognize the right object yet miss the pose offsets, boundaries, or pre-contact alignments needed for action.…

cs.LG2023

Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift

Florian Seligmann, Philipp Becker, Michael Volpp +1

Bayesian deep learning (BDL) is a promising approach to achieve well-calibrated predictions on distribution-shifted data. Nevertheless, there exists no large-scale survey that eval…

cs.RO2022

Hierarchical Policy Learning for Mechanical Search

Oussama Zenkri, Ngo Anh Vien, Gerhard Neumann

Retrieving objects from clutters is a complex task, which requires multiple interactions with the environment until the target object can be extracted. These interactions involve e…

cs.RO2017

Hybrid control trajectory optimization under uncertainty

Joni Pajarinen, Ville Kyrki, Michael Koval +3

Trajectory optimization is a fundamental problem in robotics. While optimization of continuous control trajectories is well developed, many applications require both discrete and c…

cs.RO2026

Nautilus: From One Prompt to Plug-and-Play Robot Learning

Yufeng Jin, Jianfei Guo, Xiaogang Jia +8

Robot learning research is fragmented across policy families, benchmark suites, and real robots; each implementation is entangled with the others in a complex combination matrix, m…

cs.CV2022

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

Fabian Duffhauss, Tobias Demmler, Gerhard Neumann

Estimating 6D poses of objects is an essential computer vision task. However, most conventional approaches rely on camera data from a single perspective and therefore suffer from o…

stat.ML2025

Sequential Controlled Langevin Diffusions

Junhua Chen, Lorenz Richter, Julius Berner +3

An effective approach for sampling from unnormalized densities is based on the idea of gradually transporting samples from an easy prior to the complicated target distribution. Two…

cs.RO2024

Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations

Xiaogang Jia, Denis Blessing, Xinkai Jiang +4

Imitation learning with human data has demonstrated remarkable success in teaching robots in a wide range of skills. However, the inherent diversity in human behavior leads to the…

cs.LG2026

SEAR: Sample Efficient Action Chunking Reinforcement Learning

C. F. Maximilian Nagy, Onur Celik, Emiliyan Gospodinov +4

Action chunking can improve exploration and value estimation in long horizon reinforcement learning, but makes learning substantially harder since the critic must evaluate action s…

cs.RO2018

An Algorithmic Perspective on Imitation Learning

Takayuki Osa, Joni Pajarinen, Gerhard Neumann +3

As robots and other intelligent agents move from simple environments and problems to more complex, unstructured settings, manually programming their behavior has become increasingl…

cs.RO2022

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

Moritz Reuss, Niels van Duijkeren, Robert Krug +3

It is well-known that inverse dynamics models can improve tracking performance in robot control. These models need to precisely capture the robot dynamics, which consist of well-un…

cs.LG2025

Efficient Off-Policy Learning for High-Dimensional Action Spaces

Fabian Otto, Philipp Becker, Ngo Anh Vien +1

Existing off-policy reinforcement learning algorithms often rely on an explicit state-action-value function representation, which can be problematic in high-dimensional action spac…

cs.RO2026

Agentic Language-to-Objective Synthesis for Optofluidic Assembly

Ivan Saraev, Elena Erben, Weida Liao +4

Light-based advanced manufacturing increasingly requires programmable, closed-loop tools that translate human design intent into executable operations at small length scales. Yet a…

cs.CV2023

Category-Agnostic 6D Pose Estimation with Conditional Neural Processes

Yumeng Li, Ning Gao, Hanna Ziesche +1

We present a novel meta-learning approach for 6D pose estimation on unknown objects. In contrast to ``instance-level" and ``category-level" pose estimation methods, our algorithm l…

cs.LG2026

Fourier Features Let Agents Learn High Precision Policies with Imitation Learning

Balázs Gyenes, Emiliyan Gospodinov, Jan Frieling +5

High-precision robotic manipulation requires fine-grained spatial reasoning that is often difficult to achieve with RGB-only policies due to depth ambiguity and perspective scale i…

cs.LG2026

Bridge Matching Sampler: Scalable Sampling via Generalized Fixed-Point Diffusion Matching

Denis Blessing, Lorenz Richter, Julius Berner +2

Sampling from unnormalized densities using diffusion models has emerged as a powerful paradigm. However, while recent approaches that use least-squares `matching' objectives have i…

cs.CV2023

SyMFM6D: Symmetry-aware Multi-directional Fusion for Multi-View 6D Object Pose Estimation

Fabian Duffhauss, Sebastian Koch, Hanna Ziesche +2

Detecting objects and estimating their 6D poses is essential for automated systems to interact safely with the environment. Most 6D pose estimators, however, rely on a single camer…

cs.RO2026

RayViT: Ray-Conditioned Visual Representations for Viewpoint-Robust Imitation Learning

Qian Wang, Longrui Chen, Peiran Sun +8

Visual imitation learning enables robots to acquire visuomotor skills directly from images, yet RGB observations lack explicit geometric cues, making learned policies brittle to ca…

cs.RO2026

A Multi-View 3D Telepresence System for XR Robot Teleoperation

Enes Ulas Dincer, Manuel Zaremski, Alexandra Nick +3

Robot teleoperation is critical for applications such as remote maintenance, fleet robotics, search and rescue, and data collection for robot learning. Effective teleoperation requ…

cs.RO2022

Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors

Niklas Freymuth, Nicolas Schreiber, Philipp Becker +2

Humans intuitively solve tasks in versatile ways, varying their behavior in terms of trajectory-based planning and for individual steps. Thus, they can easily generalize and adapt…

cs.LG2019

Compatible Natural Gradient Policy Search

Joni Pajarinen, Hong Linh Thai, Riad Akrour +2

Trust-region methods have yielded state-of-the-art results in policy search. A common approach is to use KL-divergence to bound the region of trust resulting in a natural gradient…

cs.RO2021

Differentiable Robust LQR Layers

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. The robust LQR layer can ex…

cs.RO2026

Scaffolding Dexterous Manipulation with Vision-Language Models

Vincent de Bakker, Joey Hejna, Tyler Ga Wei Lum +6

Dexterous robotic hands are essential for performing complex manipulation tasks, yet remain difficult to train due to the challenges of demonstration collection and high-dimensiona…

cs.RO2025

Towards Fusing Point Cloud and Visual Representations for Imitation Learning

Atalay Donat, Xiaogang Jia, Xi Huang +7

Learning for manipulation requires using policies that have access to rich sensory information such as point clouds or RGB images. Point clouds efficiently capture geometric struct…

cs.LG2026

Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference

Denis Blessing, Julius Berner, Lorenz Richter +4

Solving stochastic optimal control problems with quadratic control costs can be viewed as approximating a target path space measure, e.g. via gradient-based optimization. In practi…

cs.LG2020

Adaptation and Robust Learning of Probabilistic Movement Primitives

Sebastian Gomez-Gonzalez, Gerhard Neumann, Bernhard Schölkopf +1

Probabilistic representations of movement primitives open important new possibilities for machine learning in robotics. These representations are able to capture the variability of…

eess.SY2026

Smooth Sampling-Based Model Predictive Control Using Deterministic Samples

Markus Walker, Marcel Reith-Braun, Tai Hoang +2

Sampling-based model predictive control (MPC) is effective for nonlinear systems but often produces non-smooth control inputs due to random sampling. To address this issue, we exte…

cs.RO2023

Meta-Learning Regrasping Strategies for Physical-Agnostic Objects

Ning Gao, Jingyu Zhang, Ruijie Chen +3

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

cs.RO2021

Learning Riemannian Manifolds for Geodesic Motion Skills

Hadi Beik-Mohammadi, Søren Hauberg, Georgios Arvanitidis +2

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. This demands learnin…

cs.LG2025

Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects

Tai Hoang, Huy Le, Philipp Becker +2

Manipulating objects with varying geometries and deformable objects is a major challenge in robotics. Tasks such as insertion with different objects or cloth hanging require precis…

cs.LG2025

End-To-End Learning of Gaussian Mixture Priors for Diffusion Sampler

Denis Blessing, Xiaogang Jia, Gerhard Neumann

Diffusion models optimized via variational inference (VI) have emerged as a promising tool for generating samples from unnormalized target densities. These models create samples by…

cs.LG2022

Deep Black-Box Reinforcement Learning with Movement Primitives

Fabian Otto, Onur Celik, Hongyi Zhou +3

\Episode-based reinforcement learning (ERL) algorithms treat reinforcement learning (RL) as a black-box optimization problem where we learn to select a parameter vector of a contro…

cs.RO2024

A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics

Puze Liu, Jonas Günster, Niklas Funk +17

Machine learning methods have a groundbreaking impact in many application domains, but their application on real robotic platforms is still limited. Despite the many challenges ass…

cs.LG2024

Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations

Niklas Freymuth, Philipp Dahlinger, Tobias Würth +5

Many engineering systems require accurate simulations of complex physical systems. Yet, analytical solutions are only available for simple problems, necessitating numerical approxi…

cs.MA2018

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

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 sensi…

cs.LG2024

KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty

Philipp Becker, Niklas Freymuth, Gerhard Neumann

Probabilistic State Space Models (SSMs) are essential for Reinforcement Learning (RL) from high-dimensional, partial information as they provide concise representations for control…

cs.RO2024

Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects

Paul Maria Scheikl, Nicolas Schreiber, Christoph Haas +4

Policy learning in robot-assisted surgery (RAS) lacks data efficient and versatile methods that exhibit the desired motion quality for delicate surgical interventions. To this end,…

cond-mat.mtrl-sci2026

ATLAS: A Foundation Neural Sampler for Amorphous Materials

Mouyang Cheng, Denis Blessing, Botao Yu +4

Amorphous materials exhibit exceptional mechanical and functional properties, yet their rugged energy landscapes are notoriously difficult to sample. Below the glass-transition tem…

cs.LG2022

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

Philipp Becker, Gerhard Neumann

Improved state space models, such as Recurrent State Space Models (RSSMs), are a key factor behind recent advances in model-based reinforcement learning (RL). Yet, despite their em…

stat.ML2022

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

Maximilian Hüttenrauch, Gerhard Neumann

Most successful stochastic black-box optimizers, such as CMA-ES, use rankings of the individual samples to obtain a new search distribution. Yet, the use of rankings also introduce…

cs.LG2026

Learning Boltzmann Generators via Constrained Mass Transport

Christopher von Klitzing, Denis Blessing, Henrik Schopmans +2

Efficient sampling from high-dimensional and multimodal unnormalized probability distributions is a central challenge in many areas of science and machine learning. We focus on Bol…

cs.LG2024

Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts

Onur Celik, Aleksandar Taranovic, Gerhard Neumann

Reinforcement learning (RL) is a powerful approach for acquiring a good-performing policy. However, learning diverse skills is challenging in RL due to the commonly used Gaussian p…

cs.LG2021

Versatile Inverse Reinforcement Learning via Cumulative Rewards

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. Current approaches usually do this w…

cs.RO2026

Point Cloud Segmentation for Autonomous Clip Positioning in Laparoscopic Cholecystectomy on a Phantom

Balázs Gyenes, Nikolai Franke, Paul Maria Scheikl +5

High-risk applications in robotics, such as robot-assisted surgery, present unique challenges. These systems must be both highly precise and interpretable in order to be deployed i…

cs.LG2024

Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity

Emiliyan Gospodinov, Vaisakh Shaj, Philipp Becker +2

Developing foundational world models is a key research direction for embodied intelligence, with the ability to adapt to non-stationary environments being a crucial criterion. In t…

cs.LG2026

Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns

Dong Tian, Onur Celik, Gerhard Neumann

We introduce a sequence-conditioned critic for Soft Actor-Critic (SAC) that models trajectory context with a lightweight Transformer and trains on aggregated -step targets. Unli…

cs.CV2023

Registered and Segmented Deformable Object Reconstruction from a Single View Point Cloud

Pit Henrich, Balázs Gyenes, Paul Maria Scheikl +2

In deformable object manipulation, we often want to interact with specific segments of an object that are only defined in non-deformed models of the object. We thus require a syste…

cs.LG2023

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

Oleg Arenz, Philipp Dahlinger, Zihan Ye +2

Variational inference with Gaussian mixture models (GMMs) enables learning of highly tractable yet multi-modal approximations of intractable target distributions with up to a few h…

cs.RO2026

Towards a Multi-Embodied Grasping Agent

Roman Freiberg, Alexander Qualmann, Ngo Anh Vien +1

Multi-embodiment grasping focuses on developing approaches that exhibit generalist behavior across diverse gripper designs. Existing methods often learn the kinematic structure of…

cs.LG2022

Robot Policy Learning from Demonstration Using Advantage Weighting and Early Termination

Abdalkarim Mohtasib, Gerhard Neumann, Heriberto Cuayahuitl

Learning robotic tasks in the real world is still highly challenging and effective practical solutions remain to be found. Traditional methods used in this area are imitation learn…

cs.LG2026

Point Cloud Sequence Encoding for Material-conditioned Graph Network Simulators

Philipp Dahlinger, Balázs Gyenes, Niklas Freymuth +6

Graph Network Simulators (GNSs) have emerged as powerful surrogates for complex physics-based simulation, offering inherent differentiability and orders-of-magnitude speedups over…

cs.LG2020

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

Philipp Becker, Oleg Arenz, Gerhard Neumann

Modelling highly multi-modal data is a challenging problem in machine learning. Most algorithms are based on maximizing the likelihood, which corresponds to the M(oment)-projection…

cs.CV2026

Building Deep Graph Predictors with Graph Imitation Learning

André Eberhard, Gerhard Neumann, Pascal Friederich

Recent years have seen substantial progress in neural generation of text, images, and audio, supported by mature training pipelines and large-scale optimization. For graphs, howeve…

stat.ML2016

Policy Search with High-Dimensional Context Variables

Voot Tangkaratt, Herke van Hoof, Simone Parisi +3

Direct contextual policy search methods learn to improve policy parameters and simultaneously generalize these parameters to different context or task variables. However, learning…

cs.RO2024

Domain-Specific Fine-Tuning of Large Language Models for Interactive Robot Programming

Benjamin Alt, Urs Keßner, Aleksandar Taranovic +4

Industrial robots are applied in a widening range of industries, but robot programming mostly remains a task limited to programming experts. We propose a natural language-based ass…

cs.LG2023

Latent Task-Specific Graph Network Simulators

Philipp Dahlinger, Niklas Freymuth, Michael Volpp +2

Simulating dynamic physical interactions is a critical challenge across multiple scientific domains, with applications ranging from robotics to material science. For mesh-based sim…