Structured Neural Network Dynamics for Model-based Control
We present a structured neural network architecture that is inspired by linear time-varying dynamical systems. The network is designed to mimic the properties of linear dynamical systems which makes analysis and control simple. The architecture facilitates the integration of learned system models with gradient-based model predictive control algorithms, and removes the requirement of computing potentially costly derivatives online. We demonstrate the efficacy of this modeling technique in computing autonomous control policies through evaluation in a variety of standard continuous control domains.
Code (0)
등록된 구현이 없습니다.
Tasks
continuous-controlContinuous ControlmodelModel Predictive ControlSimilar Papers 제목 키워드 기반
SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control
In this work, we present an approach to deep visuomotor control using structured deep dynamics models. Our deep dynamics model, a variant of SE3-Nets, learns a low-dimensional pose embedding for visuomotor control via an…
DecoderUnsupervised Learning of Object Structure and Dynamics from Videos
Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stoc…
Action Recognitioncontinuous-controlContinuous ControlObject+2Structured Mechanical Models for Robot Learning and Control
Model-based methods are the dominant paradigm for controlling robotic systems, though their efficacy depends heavily on the accuracy of the model used. Deep neural networks have been used to learn models of robot dynamic…
Learning spatially structured open quantum dynamics with regional-attention transformers
Simulating the dynamics of open quantum systems with spatial structure and external control is an important challenge in quantum information science. Classical numerical solvers for such systems require integrating coupl…
BRICKS-WM: Building Reusability via Interface Composition Kinetics for Structured World Models
Model-based Reinforcement Learning (MBRL) has achieved remarkable success in continuous control by leveraging latent world models. However, prevailing approaches typically rely on monolithic latent dynamics, entangling e…
Reinforcement LearningContinuous Control