检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

452 篇 会议
27 篇 期刊文献

馆藏范围

479 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

376 篇 工学
- 255 篇 计算机科学与技术...
- 233 篇 控制科学与工程
- 86 篇 电气工程
- 73 篇 软件工程
- 51 篇 机械工程
- 30 篇 石油与天然气工程
- 20 篇 生物工程
- 17 篇 信息与通信工程
- 15 篇 力学（可授工学、理...
- 12 篇 生物医学工程（可授...
- 9 篇 动力工程及工程热...
- 8 篇 电子科学与技术（可...
- 8 篇 交通运输工程
- 6 篇 材料科学与工程（可...
- 6 篇 土木工程
- 6 篇 安全科学与工程
- 5 篇 化学工程与技术
- 5 篇 环境科学与工程（可...
- 4 篇 建筑学
- 4 篇 船舶与海洋工程
84 篇 理学
- 40 篇 数学
- 36 篇 生物学
- 28 篇 系统科学
- 20 篇 统计学（可授理学、...
- 15 篇 物理学
- 5 篇 化学
33 篇 管理学
- 28 篇 管理科学与工程(可...
- 12 篇 工商管理
10 篇 教育学
- 10 篇 教育学
9 篇 医学
3 篇 军事学
2 篇 经济学
2 篇 法学
1 篇 农学

主题

38 篇 reinforcement le...
21 篇 machine learning
18 篇 neural networks
15 篇 heuristic algori...
13 篇 adaptive control
12 篇 vehicle dynamics
12 篇 control systems
12 篇 dynamics
10 篇 optimization
10 篇 sliding mode con...
10 篇 trajectory
10 篇 deep reinforceme...
9 篇 optimal control
9 篇 robustness
8 篇 deep learning
8 篇 simulation
8 篇 robotics
7 篇 model predictive...
7 篇 nonlinear system...
7 篇 data models

机构

5 篇 mit cambridge ma...
4 篇 georgia inst tec...
4 篇 univ calif berke...
3 篇 univ calif san d...
3 篇 univ penn philad...
3 篇 stanford univ st...
3 篇 univ michigan de...
2 篇 ohio state univ ...
2 篇 duke univ durham...
2 篇 natl renewable e...
2 篇 school of electr...
2 篇 katholieke univ ...
2 篇 univ penn dept e...
2 篇 durban univ tech...
2 篇 delft univ techn...
2 篇 college of autom...
2 篇 univ bonn autono...
2 篇 zhejiang univ de...
2 篇 school of law he...
2 篇 carnegie mellon ...

作者

3 篇 vamvoudakis kyri...
3 篇 zavlanos michael...
3 篇 zhang baosen
3 篇 li na
3 篇 wang cong
3 篇 hazan elad
3 篇 cong wang
2 篇 gokdag mustafa
2 篇 soffker dirk
2 篇 michiels w.
2 篇 nakahira yorie
2 篇 cui wenqi
2 篇 zico kolter j.
2 篇 tomizuka masayos...
2 篇 fradkov alexande...
2 篇 pravesh
2 篇 levine sergey
2 篇 minasyan edgar
2 篇 pavlichenko dmyt...
2 篇 fan chuchu

语言

466 篇 英文
9 篇 其他
5 篇 中文

检索条件"任意字段=5th Annual Conference on Learning for Dynamics and Control"

共 479 条记录，以下是41-50 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Continuous Versatile Jumping Using Learned Action Residuals 5

Continuous Versatile Jumping Using Learned Action Residuals

引用

5th annual conference on learning for dynamics and control

作者： Yang, Yuxiang Meng, Xiangyun Yu, Wenhao Zhang, Tingnan Tan, Jie Boots, Byron Univ Washington Seattle WA 98195 USA Google Robot Mountain View CA USA

Jumping is essential for legged robots to traverse through difficult terrains. In this work, we propose a hierarchical framework that combines optimal control and reinforcement learning to learn continuous jumping motions for quadrupedal robots. the core of our framework is a stance controller, which combines a manually designed acceleration controller with a learned residual policy. As the acceleration controller warm starts policy for efficient training, the trained policy overcomes the limitation of the acceleration controller and improves the jumping stability. In addition, a low-level whole-body controller converts the body pose command from the stance controller to motor commands. After training in simulation, our framework can be deployed directly to the real robot, and perform versatile, continuous jumping motions, including omni-directional jumps at up to 50cm high, 60cm forward, and jump-turning at up to 90 degrees. Please visit our website for more results: https://***/view/learning- to-jump.

关键词： Legged Locomotion Robot Agility Optimal control Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Can Direct Latent Model learning Solve Linear Quadratic Gaussian control? 5

Can Direct Latent Model Learning Solve Linear Quadratic Gaus...

引用

5th annual conference on learning for dynamics and control

作者： Tian, Yi Zhang, Kaiqing Tedrake, Russ Sra, Suvrit MIT Cambridge MA 02139 USA Univ Maryland College Pk MD USA

We study the task of learning state representations from potentially high-dimensional observations, with the goal of controlling an unknown partially observable system. We pursue a direct latent model learning approach, where a dynamic model in some latent state space is learned by predicting quantities directly related to planning (e.g., costs) without reconstructing the observations. In particular, we focus on an intuitive cost-driven state representation learning method for solving Linear Quadratic Gaussian (LQG) control, one of the most fundamental partially observable control problems. As our main results, we establish finite-sample guarantees of finding a near-optimal state representation function and a near-optimal controller using the directly learned latent model. To the best of our knowledge, despite various empirical successes, prior to this work it was unclear if such a cost-driven latent model learner enjoys finite-sample guarantees. Our work underscores the value of predicting multi-step costs, an idea that is key to our theory, and notably also an idea that is known to be empirically valuable for learning state representations.

关键词： Latent model learning state representation learning for control linear quadratic Gaussian (LQG)

来源：评论

学校读者我要写书评

暂无评论

learning "Look-Ahead" Nonlocal Traffic dynamics in a Ring Road 6

Learning "Look-Ahead" Nonlocal Traffic Dynamics in a Ring Ro...

引用

6th annual learning for dynamics and control conference

作者： Zhao, Chenguang Yu, Huan Hong Kong Univ Sci & Technol Thrust Intelligent Transportat Guangzhou Peoples R China Hong Kong Univ Sci & Technol Dept Civil & Environm Engn Hong Kong Peoples R China

the macroscopic traffic flow model is widely used for traffic control and management. To incorporate drivers' anticipative behaviors and to remove impractical speed discontinuity inherent in the classic Lighthill-Whitham-Richards (LWR) traffic model, nonlocal partial differential equation (PDE) models with "look-ahead" dynamics have been proposed, which assume that the speed is a function of weighted downstream traffic density. However, it lacks data validation on two important questions: whether there exist nonlocal dynamics, and how the length and weight of the "look-ahead" window affect the spatial temporal propagation of traffic densities. In this paper, we adopt traffic trajectory data from a ring-road experiment and design a physics-informed neural network to learn the fundamental diagram and look-ahead kernel that best fit the data, and reinvent a data-enhanced nonlocal LWR model via minimizing the loss function combining the data discrepancy and the nonlocal model discrepancy. Results show that the learned nonlocal LWR yields a more accurate prediction of traffic wave propagation in three different scenarios: stop-and-go oscillations, congested, and free traffic. We first demonstrate the existence of "look-ahead" effect with real traffic data. the optimal nonlocal kernel is found out to take a length of around 35 to 50 meters, and the kernel weight within 5 meters accounts for the majority of the nonlocal effect. Our results also underscore the importance of choosing a priori physics in machine learning models.

关键词： Traffic flow model Nonlocal traffic dynamics Physics-constrained learning

来源：评论

学校读者我要写书评

暂无评论

Operator learning for Nonlinear Adaptive control 5

Operator Learning for Nonlinear Adaptive Control

引用

5th annual conference on learning for dynamics and control

作者： Bhan, Luke Shi, Yuanyuan Krstic, Miroslav Univ Calif San Diego Dept Elect & Comp Engn San Diego CA 92093 USA Univ Calif San Diego Dept Mech & Aerosp Engn San Diego CA USA

In this work, we propose an operator learning framework for accelerating nonlinear adaptive control. We define three operator mappings in adaptive control-the parameter identifier operator, the controller gain operator, and the control operator. We introduce neural operators for learning both the parameter identification mapping and the gain function mapping to produce the control action at each step. through the formalization of neural operators, we are able to learn these mappings for a wide set of different system parameter values without retraining. Empirically, we test our controller on two experiments ranging from an aircraft system (a nonlinear ODE) to a first-order hyperbolic PDE system. We demonstrate that the accuracy of both the gain function and parameter approximation can reach the magnitude of 10-4 with speedups around 98% compared to numerical solvers. Furthermore, we empirically demonstrate that despite error propagation, closed-loop stability guarantees are maintained when substituting neural operator approximations.

关键词： Neural Operators Adaptive control

来源：评论

学校读者我要写书评

暂无评论

Policy Gradient Play with Networked Agents in Markov Potential Games 5

Policy Gradient Play with Networked Agents in Markov Potenti...

引用

5th annual conference on learning for dynamics and control

作者： Aydin, Sarper Eksin, Ceyhun Texas A&M Univ College Stn TX 77843 USA

We introduce a distributed policy gradient play algorithm with networked agents playing Markov potential games. Agents have rewards at each stage of the game, that depend on the joint actions of agents given a common dynamic state. Agents implement parameterized and differentiable policies to take actions against each other. Markov potential games assume the existence of potential value functions. In a differentiable Markov potential game, partial gradients of a potential function are equal to the local gradients with respect to the individual parameters. In this work, agents receive information on other agents' parameters via a communication network in addition to rewards. Agents then use stochastic gradients with respect to local estimates of joint policy parameters to update their policy parameters. We show that agents' joint policy converges to a first-order stationary point of Markov potential value function with any type of function approximation, state and action spaces. Numerical experiments confirm the convergence result in the lake game, a Markov potential game.

关键词： Game theory reinforcement learning distributed algorithms

来源：评论

学校读者我要写书评

暂无评论

Failing with Grace: learning Neural Network controllers that are Boundedly Unsafe 5

Failing with Grace: Learning Neural Network Controllers that...

引用

5th annual conference on learning for dynamics and control

作者： Vlantis, Panagiotis Bridgeman, Leila J. Zavlanos, Michael M. Duke Univ Durham NC 27706 USA

this work considers the problem of learning a feed-forward neural network controller to safely steer an arbitrarily shaped planar robot in a compact, obstacle-occluded workspace. When training neural network controllers, existing closed-loop safety assurances impose stringent data density requirements close to the boundary of the safe state space, which are hard to satisfy in practice. We propose an approach that lifts these strong assumptions and instead admits graceful safety violations, i.e., of a bounded, spatially controlled magnitude. the method employs reachability analysis techniques to include safety constraints in the training process. the method can simultaneously learn a safe vector field for the closed-loop system and provide proven numerical worst-case bounds on safety violations over the whole configuration space, defined by the overlap between an over-approximation of the closed-loop system's forward reachable set and the set of unsafe states.

关键词： Safe learning neural network control reachability analysis

来源：评论

学校读者我要写书评

暂无评论

Modified Policy Iteration for Exponential Cost Risk Sensitive MDPs 5

Modified Policy Iteration for Exponential Cost Risk Sensitiv...

引用

5th annual conference on learning for dynamics and control

作者： Murthy, Yashaswini Moharrami, Mehrdad Srikant, R. Univ Illinois Champaign IL 61820 USA

Modified policy iteration (MPI) also known as optimistic policy iteration is at the core of many reinforcement learning algorithms. It works by combining elements of policy iteration and value iteration. the convergence of MPI has been well studied in the case of discounted and average-cost MDPs. In this work, we consider the exponential cost risk-sensitive MDP formulation, which is known to provide some robustness to model parameters. Although policy iteration and value iteration have been well studied in the context of risk sensitive MDPs, modified policy iteration is relatively unexplored. We provide the first proof that MPI also converges for the risk-sensitive problem in the case of finite state and action spaces. Since the exponential cost formulation deals with the multiplicative Bellman equation, our main contribution is a convergence proof which is quite different than existing results for discounted and risk-neutral average-cost problems.

关键词： Robust stochastic control dynamic programming risk-sensitive stochastic control

来源：评论

学校读者我要写书评

暂无评论

Contrastive Example-Based control 5

Contrastive Example-Based Control

引用

5th annual conference on learning for dynamics and control

作者： Hatch, Kyle Eysenbach, Benjamin Rafailov, Rafael Yu, Tianhe Salakhutdinov, Ruslan Levine, Sergey Finn, Chelsea Stanford Univ Dept Comp Sci Stanford CA 94305 USA Carnegie Mellon Univ Machine Learning Dept Pittsburgh PA USA Univ Calif Berkeley Dept Elect Engn & Comp Sci Berkeley CA USA

While many real-world problems that might benefit from reinforcement learning, these problems rarely fit into the MDP mold: interacting with the environment is often expensive and specifying reward functions is challenging. Motivated by these challenges, prior work has developed data-driven approaches that learn entirely from samples from the transition dynamics and examples of high-return states. these methods typically learn a reward function from high-return states, use that reward function to label the transitions, and then apply an offline RL algorithm to these transitions. While these methods can achieve good results on many tasks, they can be complex, often requiring regularization and temporal difference updates. In this paper, we propose a method for offline, example-based control that learns an implicit model of multi-step transitions, rather than a reward function. We show that this implicit model can represent the Q-values for the example-based control problem. Across a range of state-based and image-based offline control tasks, our method outperforms baselines that use learned reward functions;additional experiments demonstrate improved robustness and scaling with dataset size.

关键词： reinforcement learning offline RL robot learning reward learning contrastive learning model-based reinforcement learning example-based control reward-free learning

来源：评论

学校读者我要写书评

暂无评论

Roll-Drop: accounting for observation noise with a single parameter 5

Roll-Drop: accounting for observation noise with a single pa...

引用

5th annual conference on learning for dynamics and control

作者： Campanaro, Luigi De Martini, Daniele Gangapurwala, Siddhant Merkt, Wolfgang Havoutis, Ioannis Univ Oxford Dept Engn Sci Oxford England

this paper proposes a simple strategy for sim-to-real in Deep-Reinforcement learning (DRL) - called Roll-Drop - that uses dropout during simulation to account for observation noise during deployment without explicitly modelling its distribution for each state. DRL is a promising approach to control robots for highly dynamic and feedback-based manoeuvres, and accurate simulators are crucial to providing cheap and abundant data to learn the desired behaviour. Nevertheless, the simulated data are noiseless and generally show a distributional shift that challenges the deployment on real machines where sensor readings are affected by noise. the standard solution is modelling the latter and injecting it during training;while this requires a thorough system identification, Roll-Drop enhances the robustness to sensor noise by tuning only a single parameter. We demonstrate an 80% success rate when up to 25% noise is injected in the observations, with twice higher robustness than the baselines. We deploy the controller trained in simulation on a Unitree A1 platform and assess this improved robustness on the physical system. Additional resources at: https://***/***/roll-drop

关键词： Sim-to-real Legged Locomotion Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Regret Analysis of Online LQR control via Trajectory Prediction and Tracking 5

Regret Analysis of Online LQR Control via Trajectory Predict...

引用

5th annual conference on learning for dynamics and control

作者： Chen, Yitian Molloy, Timothy L. Summers, Tyler Shames, Iman Australian Natl Univ CIICADA Lab Canberra ACT Australia Univ Texas Dallas Richardson TX 75083 USA

In this paper, we propose and analyse a new method for online linear quadratic regulator (LQR) control with a priori unknown time-varying cost matrices. the cost matrices are revealed sequentially with the potential for future values to be previewed over a short window. Our novel method involves using the available cost matrices to predict the optimal trajectory, and a tracking controller to drive the system towards it. We adopted the notion of dynamic regret to measure the performance of this proposed online LQR control method, with our main result being that the (dynamic) regret of our method is upper bounded by a constant. Moreover, the regret upper bound decays exponentially with the preview window length, and is extendable to systems with disturbances. We show in simulations that our proposed method offers improved performance compared to other previously proposed online LQR methods.

关键词： Online LQR Dynamic Regret Trajectory tracking

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共48页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：