| Recurrent kalman networks: Factorized inference in high-dimensional deep feature spaces P Becker, H Pandya, G Gebhardt, C Zhao, CJ Taylor, G Neumann International Conference on Machine Learning, 544-552, 2019 | 97 | 2019 |
| Specializing Versatile Skill Libraries using Local Mixture of Experts O Celik, D Zhou, G Li, P Becker, G Neumann 5th Annual Conference on Robot Learning, 2021 | 31 | 2021 |
| Differentiable Trust Region Layers for Deep Reinforcement Learning F Otto, P Becker, NA Vien, HC Ziesche, G Neumann arXiv preprint arXiv:2101.09207, 2021 | 27 | 2021 |
| Expected information maximization: Using the i-projection for mixture density estimation P Becker, O Arenz, G Neumann arXiv preprint arXiv:2001.08682, 2020 | 12 | 2020 |
| Action-conditional recurrent kalman networks for forward and inverse dynamics learning V Shaj, P Becker, D Büchler, H Pandya, N van Duijkeren, CJ Taylor, ... Conference on Robot Learning, 765-781, 2021 | 10 | 2021 |
| Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios V Shaj Kumar, D Büchler, R Sonker, P Becker, G Neumann arXiv preprint arXiv:2206.14697, 2022 | 7 | 2022 |
| On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning P Becker, G Neumann Transactions on Machine Learning Research, 2022 | 5 | 2022 |
| End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Control M Reuss, N van Duijkeren, R Krug, P Becker, V Shaj, G Neumann arXiv preprint arXiv:2205.13804, 2022 | 5 | 2022 |
| Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift F Seligmann, P Becker, M Volpp, G Neumann Advances in Neural Information Processing Systems 36, 2024 | 4 | 2024 |
| Joint Representations for Reinforcement Learning with Multiple Sensors P Becker, S Markgraf, F Otto, G Neumann | 4* | 2023 |
| Switching Recurrent Kalman Networks G Nguyen-Quynh, P Becker, C Qiu, M Rudolph, G Neumann arXiv preprint arXiv:2111.08291, 2021 | 4 | 2021 |
| Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors N Freymuth, N Schreiber, P Becker, A Taranovic, G Neumann arXiv preprint arXiv:2210.08121, 2022 | 3 | 2022 |
| Curriculum-Based Imitation of Versatile Skills MX Li, O Celik, P Becker, D Blessing, R Lioutikov, G Neumann 2023 IEEE International Conference on Robotics and Automation (ICRA), 2951-2957, 2023 | 2 | 2023 |
| Accurate Bayesian Meta-Learning by Accurate Task Posterior Inference M Volpp, P Dahlinger, P Becker, C Daniel, G Neumann The Eleventh International Conference on Learning Representations, 2023 | 2 | 2023 |
| Versatile Inverse Reinforcement Learning via Cumulative Rewards N Freymuth, P Becker, G Neumann arXiv preprint arXiv:2111.07667, 2021 | 2 | 2021 |
| KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty P Becker, N Freymuth, G Neumann arXiv preprint arXiv:2406.15131, 2024 | | 2024 |
| Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations N Freymuth, P Dahlinger, T Würth, P Becker, A Taranovic, O Grönheim, ... arXiv preprint arXiv:2406.14161, 2024 | | 2024 |
| Vlearn: Off-Policy Learning with Efficient State-Value Function Estimation F Otto, P Becker, VA Ngo, G Neumann arXiv preprint arXiv:2403.04453, 2024 | | 2024 |
| Information-Theoretic Trust Regions for Stochastic Gradient-Based Optimization P Dahlinger, P Becker, M Hüttenrauch, G Neumann arXiv preprint arXiv:2310.20574, 2023 | | 2023 |
| Episode Transformer: Model-based Episodic Reinforcement Learning R Jacob, V Shaj, P Becker, G Neumann | | |
Gerhard NeumannProfessor, Karlsruhe Institute of Technology (KIT)在 robot-learning.de 的电子邮件经过验证
