Gerhard Neumann

DIME: Diffusion-Based Maximum Entropy Reinforcement Learning ICML 2025 Efficient Off-Policy Learning for High-Dimensional Action Spaces ICLR 2025 End-to-end Learning of Gaussian Mixture Priors for Diffusion Sampler ICLR 2025 Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects ICLR 2025 IRIS: An Immersive Robot Interaction System CoRL 2025 Sequential Controlled Langevin Diffusions ICLR 2025 TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning ICLR 2025 Underdamped Diffusion Bridges with Applications to Sampling ICLR 2025 Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts ICML 2024 A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics NeurIPS 2024 Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling ICML 2024 MaIL: Improving Imitation Learning with Selective State Space Models CoRL 2024 Neural Contractive Dynamical Systems ICLR 2024 Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning ICLR 2024 PointPatchRL - Masked Reconstruction Improves Reinforcement Learning on Point Clouds CoRL 2024 Registered and Segmented Deformable Object Reconstruction From a Single View Point Cloud WACV 2024 Robust Black-Box Optimization for Stochastic Search and Episodic Reinforcement Learning JMLR 2024 Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations ICLR 2024 Variational Distillation of Diffusion Policies into Mixture of Experts NeurIPS 2024 Accurate Bayesian Meta-Learning by Accurate Task Posterior Inference ICLR 2023 Adversarial Imitation Learning with Preferences ICLR 2023 Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift NeurIPS 2023 Grounding Graph Network Simulators using Physical Sensor Observations ICLR 2023 Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills NeurIPS 2023 LapGym - An Open Source Framework for Reinforcement Learning in Robot-Assisted Laparoscopic Surgery JMLR 2023 Multi Time Scale World Models NeurIPS 2023 SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objects CoRL 2023 Swarm Reinforcement Learning for Adaptive Mesh Refinement NeurIPS 2023 Deep Black-Box Reinforcement Learning with Movement Primitives CoRL 2022 End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Control RSS 2022 FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion ECCV 2022 Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios ICLR 2022 Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors CoRL 2022 What Matters for Meta-Learning Vision Regression Tasks? CVPR 2022 Bayesian Context Aggregation for Neural Processes ICLR 2021 Differentiable Trust Region Layers for Deep Reinforcement Learning ICLR 2021 Learning Riemannian Manifolds for Geodesic Motion Skills RSS 2021 Specializing Versatile Skill Libraries using Local Mixture of Experts CoRL 2021 Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning CoRL 2020 Expected Information Maximization: Using the I-Projection for Mixture Density Estimation ICLR 2020 Trust-Region Variational Inference with Gaussian Mixture Models JMLR 2020 Deep Reinforcement Learning for Swarm Systems JMLR 2019 Projections for Approximate Policy Iteration Algorithms ICML 2019 Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces ICML 2019 Efficient Gradient-Free Variational Inference using Policy Search ICML 2018 Model-Free Trajectory-based Policy Optimization with Monotonic Improvement JMLR 2018 A Survey of Preference-Based Reinforcement Learning Methods JMLR 2017 Contextual Covariance Matrix Adaptation Evolutionary Strategies IJCAI 2017 Local Bayesian Optimization of Motor Skills ICML 2017 Non-parametric Policy Search with Limited Information Loss JMLR 2017 Catching heuristics are optimal control policies NeurIPS 2016 Hierarchical Relative Entropy Policy Search JMLR 2016 Model-Free Trajectory Optimization for Reinforcement Learning ICML 2016 Learning of Non-Parametric Control Policies with High-Dimensional State Features AISTATS 2015 Model-Based Relative Entropy Stochastic Search NeurIPS 2015 Policy Evaluation with Temporal Differences: A Survey and Comparison JMLR 2014 Probabilistic Movement Primitives NeurIPS 2013 Hierarchical Relative Entropy Policy Search AISTATS 2012 Fitted Q-iteration by Advantage Weighted Regression NeurIPS 2008