检索结果-内蒙古大学图书馆

Data-Rate and Network Coding Co-Design With Stability And Capacity Constraints

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2017年第1期50卷 6397-6402页

作者： Di Girolamo G.D. Di Benedetto M.D. Dilip A.S.A. Jungers R. Department of Information Engineering Computer Science and Mathematics Centre of Excellence DEWS University of L'Aquila Italy UC Louvain Institute of Information and Communication Technologies Electronics and Applied Mathematics (ICTEAM) Italy

Related to Networked Control Systems, the interaction between information theory and control theory is expected to be more and more important to improve the performance of control loops closed over wireless communication networks. In this work, we consider quantized state measurements relayed to a controller via a communication network adopting the standard network coding model. We address and solve the optimal co-design of data-rate and network coding with stability and capacity constraints. We show that such problem can be formalised as a Mixed Integer Linear Program where data-rates are the continuous variables and network coding coefficients are the binary variables. We show with an illustrative example that exploiting our modeling framework and method, it is possible to stabilise control loops that cannot be stabilised using the existing methods in the literature. © 2017

关键词： control of network systems Control over networks Control under communication constraints Mixed Integer Linear Optimization Optimization Quantized systems

Ten simple rules for reproducible research in jupyter notebooks

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Rule, Adam Birmingham, Amanda Zuniga, Cristal Altintas, Ilkay Huang, Shih-Cheng Knight, Rob Moshiri, Niema Nguyen, Mai H. Rosenthal, Sara Brin Pérez, Fernando Rose, Peter W. Design Lab UC San Diego San DiegoCA United States Center for Computational Biology and Bioinformatics UC San Diego San DiegoCA United States Department of Pediatrics UC San Diego San DiegoCA United States Data Science Hub San Diego Supercomputer Center UC San Diego San DiegoCA United States Departments of Bioengineering and Computer Science and Engineering Center for Microbiome Innovation UC San Diego San DiegoCA United States Bioinformatics and Systems Biology Graduate Program UC San Diego San DiegoCA United States Department of Statistics Berkeley Institute for Data Science UC Berkeley Lawrence Berkeley National Laboratory BerkeleyCA United States Biomedical Informatics Graduate Program Stanford University StanfordCA United States

Reproducibility of computational studies is a hallmark of scientific methodology. It enables researchers to build with confidence on the methods and findings of others, reuse and extend computational pipelines, and thereby drive scientific progress. Since many experimental studies rely on computational analyses, biologists need guidance on how to set up and document reproducible data analyses or simulations. In this paper, we address several questions about reproducibility. For example, what are the technical and non-technical barriers to reproducible computational studies? What opportunities and challenges do computational notebooks offer to overcome some of these barriers? What tools are available and how can they be used effectively? We have developed a set of rules to serve as a guide to scientists with a specific focus on computational notebook systems, such as Jupyter Notebooks, which have become a tool of choice for many applications. Notebooks combine detailed workflows with narrative text and visualization of results. Combined with software repositories and open source licensing, notebooks are powerful tools for transparent, collaborative, reproducible, and reusable data analyses. Copyright © 2018, The Authors. All rights reserved.

关键词： Digital storage

Pid2018 benchmark challenge: Multi-objective stochastic optimization algorithm

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Ates, Abdullah Yuan, Jie Dehghan, Sina Zhao, Yang Yeroglu, Celaleddin Chen, YangQuan Inonu University Computer Engineering Department Malatya44280 Turkey School of Automation Southeast University Nanjing210096 China UC Merced Mechanical Engineering Departments MESA Lab MercedCA95301 United States School of Control Science and Engineering Shandong University Jinan250061 China

This paper presents a multi-objective stochastic optimization method for tuning of the controller parameters of Refrigeration Systems based on Vapour Compression. Stochastic Multi Parameter Divergence Optimization (SMDO) algorithm is modified for minimization of the Multi Objective function for optimization process. System control performance is improved by tuning of the PI controller parameters according to discrete time model of the refrigeration system with multi objective function by adding conditional integral structure that is preferred to reduce the steady state error of the system. Simulations are compared with existing results via many graphical and numerical solutions. Copyright © 2018, The Authors. All rights reserved.

关键词： Stochastic systems

Sim-to-real transfer of robotic control with dynamics randomization

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Peng, Xue Bin Andrychowicz, Marcin Zaremba, Wojciech Abbeel, Pieter OpenAI UC Berkeley Department of Electrical Engineering and Computer Science

Simulations are attractive environments for training agents as they provide an abundant source of data and alleviate certain safety concerns during the training process. But the behaviours developed by agents in simulation are often specific to the characteristics of the simulator. Due to modeling error, strategies that are successful in simulation may not transfer to their real world counterparts. In this paper, we demonstrate a simple method to bridge this "reality gap". By randomizing the dynamics of the simulator during training, we are able to develop policies that are capable of adapting to very different dynamics, including ones that differ significantly from the dynamics on which the policies were trained. This adaptivity enables the policies to generalize to the dynamics of the real world without any training on the physical system. Our approach is demonstrated on an object pushing task using a robotic arm. Despite being trained exclusively in simulation, our policies are able to maintain a similar level of performance when deployed on a real robot, reliably moving an object to a desired location from random initial configurations. We explore the impact of various design decisions and show that the resulting policies are robust to significant calibration error. Copyright © 2017, The Authors. All rights reserved.

关键词： Dynamics

Learning invariant feature spaces to transfer skills with reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Gupta, Abhishek Devin, Coline Liu, YuXuan Abbeel, Pieter Levine, Sergey UC Berkeley Department of Electrical Engineering and Computer Science OpenAI

People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures. This can accelerate acquisition of new skills even when the observed agent differs substantially from the learning agent in terms of morphology. In this paper, we examine how reinforcement learning algorithms can transfer knowledge between morphologically different agents (e.g., different robots). We introduce a problem formulation where two agents are tasked with learning multiple skills by sharing information. Our method uses the skills that were learned by both agents to train invariant feature spaces that can then be used to transfer other skills from one agent to another. The process of learning these invariant feature spaces can be viewed as a kind of "analogy making," or implicit learning of partial correspondences between two distinct domains. We evaluate our transfer learning algorithm in two simulated robotic manipulation skills, and illustrate that we can transfer knowledge between simulated robotic arms with different numbers of links, as well as simulated arms with different actuation mechanisms, where one robot is torque-driven while the other is tendon-driven. Copyright © 2017, The Authors. All rights reserved.

关键词： Reinforcement learning

Imitation from observation: Learning to imitate behaviors from raw video via context translation

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Liu, YuXuan Gupta, Abhishek Abbeel, Pieter Levine, Sergey UC Berkeley Department of Electrical Engineering and Computer Science OpenAI

Imitation learning is an effective approach for autonomous systems to acquire control policies when an explicit reward function is unavailable, using supervision provided as demonstrations from an expert, typically a human operator. However, standard imitation learning methods assume that the agent receives examples of observation-action tuples that could be provided, for instance, to a supervised learning algorithm. This stands in contrast to how humans and animals imitate: we observe another person performing some behavior and then figure out which actions will realize that behavior, compensating for changes in viewpoint, surroundings, object positions and types, and other factors. We term this kind of imitation learning "imitation-from-observation," and propose an imitation learning method based on video prediction with context translation and deep reinforcement learning. This lifts the assumption in imitation learning that the demonstration should consist of observations in the same environment configuration, and enables a variety of interesting applications, including learning robotic skills that involve tool use simply by observing videos of human tool use. Our experimental results show the effectiveness of our approach in learning a wide range of real-world robotic tasks modeled after common household chores from videos of a human demonstrator, including sweeping, ladling almonds, pushing objects as well as a number of tasks in simulation. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep learning

Deep object-centric representations for generalizable robot learning

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Devin, Coline Abbeel, Pieter Darrell, Trevor Levine, Sergey UC Berkeley Department of Electrical Engineering and Computer Science OpenAI

Robotic manipulation in complex open-world scenarios requires both reliable physical manipulation skills and effective and generalizable perception. In this paper, we propose a method where general purpose pretrained visual models serve as an object-centric prior for the perception system of a learned policy. We devise an object-level attentional mechanism that can be used to determine relevant objects from a few trajectories or demonstrations, and then immediately incorporate those objects into a learned policy. A task-independent meta-attention locates possible objects in the scene, and a task-specific attention identifies which objects are predictive of the trajectories. The scope of the task-specific attention is easily adjusted by showing demonstrations with distractor objects or with diverse relevant objects. Our results indicate that this approach exhibits good generalization across object instances using very few samples, and can be used to learn a variety of manipulation tasks using reinforcement learning. Copyright © 2017, The Authors. All rights reserved.

关键词： Reinforcement learning

Phase Coexistence of Ferroelectric Vortices and Classical a1/a2 Domains in PbTiO3/SrTiO3 Superlattices.

学校读者我要写书评

暂无评论

Microscopy and Microanalysis 2018年第S1期24卷 1638-1639页

作者： Christopher T. Nelson Zijian Hong Ajay K. Yadav Anoop R. Damodaran Shang-Lin Hsu James D. Clarkson Long-Qing Chen Lane W. Martin Ramamoorthy Ramesh Materials Science & Technology Division Oak Ridge National Laboratory Oak Ridge TN USA Department of Physics University of California Berkeley CA USA Materials Sciences Division Lawrence Berkeley National Laboratory Berkeley CA USA Department of Materials Science and Engineering Pennsylvania State University State College PA USA Department of Materials Science and Engineering University of California Berkeley CA USA School of Electrical Engineering and Computer Science UC Berkeley Berkeley California USA.

Reinforcement learning with deep energy-based policies

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Haarnoja, Tuomas Tang, Haoran Abbeel, Pieter Levine, Sergey Uc Berkeley Department of Electrical Engineering and Computer Sciences Uc Berkeley Department of Mathematics OpenAI International Computer Science Institute

We propose a method for learning expressive energy-based policies for continuous states and actions, which has been feasible only in tabular domains before. We apply our method to learning maximum entropy policies, resulting into a new algorithm, called soft Q-learning, that expresses the optimal policy via a Boltzmann distribution. We use the recently proposed amortized Stein variational gradient descent to learn a stochastic sampling network that approximates samples from this distribution. The benefits of the proposed algorithm include improved exploration and compositionality that allows transferring skills between tasks, which we confirm in simulated experiments with swimming and walking robots. We also draw a connection to actorcritic methods, which can be viewed performing approximate inference on the corresponding energy-based model.

关键词： Reinforcement learning