Zobrazeno 1 - 10
of 499
pro vyhledávání: '"Neumann, Gerhard"'
Autor:
Kienle, Claudius, Alt, Benjamin, Celik, Onur, Becker, Philipp, Katic, Darko, Jäkel, Rainer, Neumann, Gerhard
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-consuming endeavor. Existing approaches for learning or optimizing thes
Externí odkaz:
http://arxiv.org/abs/2407.15660
Probabilistic State Space Models (SSMs) are essential for Reinforcement Learning (RL) from high-dimensional, partial information as they provide concise representations for control. Yet, they lack the computational efficiency of their recent determin
Externí odkaz:
http://arxiv.org/abs/2406.15131
Autor:
Freymuth, Niklas, Dahlinger, Philipp, Würth, Tobias, Becker, Philipp, Taranovic, Aleksandar, Grönheim, Onno, Kärger, Luise, Neumann, Gerhard
Many engineering systems require accurate simulations of complex physical systems. Yet, analytical solutions are only available for simple problems, necessitating numerical approximations such as the Finite Element Method (FEM). The cost and accuracy
Externí odkaz:
http://arxiv.org/abs/2406.14161
Autor:
Zhou, Hongyi, Blessing, Denis, Li, Ge, Celik, Onur, Jia, Xiaogang, Neumann, Gerhard, Lioutikov, Rudolf
This work introduces Variational Diffusion Distillation (VDD), a novel method that distills denoising diffusion policies into Mixtures of Experts (MoE) through variational inference. Diffusion Models are the current state-of-the-art in generative mod
Externí odkaz:
http://arxiv.org/abs/2406.12538
Autor:
Freymuth, Niklas, Dahlinger, Philipp, Würth, Tobias, Reisch, Simon, Kärger, Luise, Neumann, Gerhard
Simulating physical systems is essential in engineering, but analytical solutions are limited to straightforward problems. Consequently, numerical methods like the Finite Element Method (FEM) are widely used. However, the FEM becomes computationally
Externí odkaz:
http://arxiv.org/abs/2406.08440
Autor:
Jia, Xiaogang, Wang, Qian, Donat, Atalay, Xing, Bowen, Li, Ge, Zhou, Hongyi, Celik, Onur, Blessing, Denis, Lioutikov, Rudolf, Neumann, Gerhard
This work introduces Mamba Imitation Learning (MaIL), a novel imitation learning (IL) architecture that offers a computationally efficient alternative to state-of-the-art (SoTA) Transformer policies. Transformer-based policies have achieved remarkabl
Externí odkaz:
http://arxiv.org/abs/2406.08234
Monte Carlo methods, Variational Inference, and their combinations play a pivotal role in sampling from intractable probability distributions. However, current studies lack a unified evaluation framework, relying on disparate performance measures and
Externí odkaz:
http://arxiv.org/abs/2406.07423
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 policy parameterization. We propose \textbf{Di}verse \textbf{Skil}l \te
Externí odkaz:
http://arxiv.org/abs/2403.06966
Existing off-policy reinforcement learning algorithms often rely on an explicit state-action-value function representation, which can be problematic in high-dimensional action spaces due to the curse of dimensionality. This reliance results in data i
Externí odkaz:
http://arxiv.org/abs/2403.04453
Autor:
Jia, Xiaogang, Blessing, Denis, Jiang, Xinkai, Reuss, Moritz, Donat, Atalay, Lioutikov, Rudolf, Neumann, Gerhard
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 emergence of multi-modal data distributions, thereby presenting a form
Externí odkaz:
http://arxiv.org/abs/2402.14606