Zobrazeno 1 - 10
of 407
pro vyhledávání: '"Differentiable simulation"'
The sample inefficiency of reinforcement learning (RL) remains a significant challenge in robotics. RL requires large-scale simulation and, still, can cause long training times, slowing down research and innovation. This issue is particularly pronoun
Externí odkaz:
http://arxiv.org/abs/2410.15979
Autor:
Bagajo, Joshua, Schwarke, Clemens, Klemm, Victor, Georgiev, Ignat, Sleiman, Jean-Pierre, Tordesillas, Jesus, Garg, Animesh, Hutter, Marco
Differentiable simulators provide analytic gradients, enabling more sample-efficient learning algorithms and paving the way for data intensive learning tasks such as learning from images. In this work, we demonstrate that locomotion policies trained
Externí odkaz:
http://arxiv.org/abs/2411.02189
Identifying predictive world models for robots in novel environments from sparse online observations is essential for robot task planning and execution in novel environments. However, existing methods that leverage differentiable simulators to identi
Externí odkaz:
http://arxiv.org/abs/2412.00259
First-order Policy Gradient (FoPG) algorithms such as Backpropagation through Time and Analytical Policy Gradients leverage local simulation physics to accelerate policy search, significantly improving sample efficiency in robot control compared to s
Externí odkaz:
http://arxiv.org/abs/2410.03076
Current methods to learn controllers for autonomous vehicles (AVs) focus on behavioural cloning. Being trained only on exact historic data, the resulting agents often generalize poorly to novel scenarios. Simulators provide the opportunity to go beyo
Externí odkaz:
http://arxiv.org/abs/2409.07965
Over the past few years, robotics simulators have largely improved in efficiency and scalability, enabling them to generate years of simulated data in a few hours. Yet, efficiently and accurately computing the simulation derivatives remains an open c
Externí odkaz:
http://arxiv.org/abs/2409.07107
Model-Free Reinforcement Learning (MFRL), leveraging the policy gradient theorem, has demonstrated considerable success in continuous control tasks. However, these approaches are plagued by high gradient variance due to zeroth-order gradient estimati
Externí odkaz:
http://arxiv.org/abs/2405.17784
Autor:
Song, Yunlong, Scaramuzza, Davide
Control systems are at the core of every real-world robot. They are deployed in an ever-increasing number of applications, ranging from autonomous racing and search-and-rescue missions to industrial inspections and space exploration. To achieve peak
Externí odkaz:
http://arxiv.org/abs/2407.01568
We introduce a method for manipulating objects in three-dimensional space using controlled fluid streams. To achieve this, we train a neural network controller in a differentiable simulation and evaluate it in a simulated environment consisting of an
Externí odkaz:
http://arxiv.org/abs/2404.18181
Autor:
Li, Yifei, Sun, Yuchen, Ma, Pingchuan, Sifakis, Eftychios, Du, Tao, Zhu, Bo, Matusik, Wojciech
We present a novel framework to explore neural control and design of complex fluidic systems with dynamic solid boundaries. Our system features a fast differentiable Navier-Stokes solver with solid-fluid interface handling, a low-dimensional differen
Externí odkaz:
http://arxiv.org/abs/2405.14903