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

751 篇 会议
272 篇 期刊文献
4 册 图书

馆藏范围

1,027 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

719 篇 工学
- 523 篇 计算机科学与技术...
- 385 篇 电气工程
- 284 篇 控制科学与工程
- 153 篇 软件工程
- 83 篇 信息与通信工程
- 41 篇 交通运输工程
- 24 篇 仪器科学与技术
- 21 篇 机械工程
- 9 篇 电子科学与技术（可...
- 9 篇 生物工程
- 7 篇 力学（可授工学、理...
- 7 篇 土木工程
- 7 篇 石油与天然气工程
- 6 篇 动力工程及工程热...
- 4 篇 材料科学与工程（可...
- 4 篇 生物医学工程（可授...
- 4 篇 安全科学与工程
- 3 篇 化学工程与技术
- 3 篇 航空宇航科学与技...
120 篇 理学
- 98 篇 数学
- 31 篇 系统科学
- 22 篇 统计学（可授理学、...
- 10 篇 生物学
- 9 篇 物理学
- 5 篇 化学
68 篇 管理学
- 65 篇 管理科学与工程(可...
- 14 篇 工商管理
- 7 篇 图书情报与档案管...
5 篇 经济学
- 4 篇 应用经济学
3 篇 法学
- 3 篇 社会学
2 篇 医学
1 篇 教育学

主题

315 篇 reinforcement le...
216 篇 dynamic programm...
206 篇 optimal control
110 篇 adaptive dynamic...
105 篇 adaptive dynamic...
97 篇 learning
88 篇 neural networks
79 篇 heuristic algori...
67 篇 reinforcement le...
58 篇 learning (artifi...
54 篇 nonlinear system...
52 篇 convergence
52 篇 control systems
51 篇 mathematical mod...
48 篇 approximate dyna...
44 篇 approximation al...
43 篇 equations
42 篇 adaptive control
41 篇 cost function
40 篇 artificial neura...

机构

41 篇 chinese acad sci...
27 篇 univ rhode isl d...
17 篇 tianjin univ sch...
16 篇 northeastern uni...
16 篇 univ sci & techn...
16 篇 univ illinois de...
14 篇 beijing normal u...
13 篇 northeastern uni...
13 篇 guangdong univ t...
12 篇 northeastern uni...
9 篇 natl univ def te...
8 篇 ieee
8 篇 univ chinese aca...
7 篇 univ chinese aca...
7 篇 cent south univ ...
7 篇 southern univ sc...
7 篇 beijing univ tec...
6 篇 chinese acad sci...
6 篇 missouri univ sc...
5 篇 nanjing univ pos...

作者

55 篇 liu derong
37 篇 wei qinglai
29 篇 he haibo
22 篇 wang ding
21 篇 xu xin
19 篇 jiang zhong-ping
17 篇 lewis frank l.
17 篇 yang xiong
17 篇 zhang huaguang
17 篇 ni zhen
16 篇 zhao bo
16 篇 gao weinan
14 篇 zhao dongbin
13 篇 zhong xiangnan
12 篇 si jennie
12 篇 derong liu
11 篇 song ruizhuo
10 篇 jagannathan s.
10 篇 dongbin zhao
9 篇 abouheaf mohamme...

语言

970 篇 英文
51 篇 其他
6 篇 中文

检索条件"任意字段=IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning"

共 1027 条记录，以下是811-820 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：

A Strategy for Converging dynamic Action Policies

A Strategy for Converging Dynamic Action Policies

引用

ieee symposium on Intelligent Agents

作者： Ribeiro, Richardson Borges, Andre P. Koerich, Alessandro L. Scalabrin, Edson E. Enembreck, Fabricio Univ Contestado UnC2 Av Nereu Ramos 1071 BR-89300000 Mafra SC Brazil Pontifical Catholic Univ Parana PUCPR Grad Program Comp Sci PPGIa B-1155 Parana Brazil

ISBN: (纸本)9781424427673

In this paper we propose a novel strategy for converging dynamic policies generated by adaptive agents, which receive and accumulate rewards for their actions. The goal of the proposed strategy is to speed up the convergence of such agents to a good policy in dynamic environments. Since it is difficult to have the good value for a state due to the continuous changing in the environment, previous policies are kept in memory for reuse in future policies, avoiding delays or unexpected speedups in the agent's learning. Experimental results on dynamic environments with different policies have shown that the proposed strategy is able to speed up the convergence of the agent while achieving good action policies.

关键词： adaptive Agents dynamic Environments reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

adaptive computation of optimal nonrandomized policies in constrained average-reward MDPs

Adaptive computation of optimal nonrandomized policies in co...

引用

ieee symposium on adaptive dynamic programming and reinforcement learning, (ADPRL)

作者： Eugene A. Feinberg Department of Applied Mathematics and Statistics Stony Brook University Stony Brook NY USA

This paper deals with computation of optimal nonrandomized nonstationary policies and mixed stationary policies for average-reward Markov decision processes with multiple criteria and constraints. We consider problems with finite state and action sets satisfying the unichain condition. The described procedure for computing optimal nonrandomized policies can also be used for adaptive control problems.

关键词： Frequency adaptive control Vectors Linear programming Constraint theory Mathematics Statistics State-space methods Probability distribution

来源：评论

学校读者我要写书评

暂无评论

Feature discovery in approximate dynamic programming

Feature discovery in approximate dynamic programming

引用

ieee symposium on adaptive dynamic programming and reinforcement learning, (ADPRL)

作者： Philippe Preux Sertan Girgin Manuel Loth Laboratoire dInformatique Fondamentale de Lille (Computer Science Laboratory associated to the CNRS) and the INRIAINRIA Université de Lille France

Feature discovery aims at finding the best representation of data. This is a very important topic in machine learning, and in reinforcement learning in particular. Based on our recent work on feature discovery in the context of reinforcement learning to discover a good, if not the best, representation of states, we report here on the use of the same kind of approach in the context of approximate dynamic programming. The striking difference with the usual approach is that we use a non parametric function approximator to represent the value function, instead of a parametric one. We also argue that the problem of discovering the best state representation and the problem of the value function approximation are just the two faces of the same coin, and that using a non parametric approach provides an elegant solution to both problems at once.

关键词： dynamic programming Function approximation Games Machine learning Acceleration Computer science Software tools Artificial intelligence Velocity control Control systems

来源：评论

学校读者我要写书评

暂无评论

Using reward-weighted imitation for robot reinforcement learning

Using reward-weighted imitation for robot Reinforcement Lear...

引用

ieee symposium on adaptive dynamic programming and reinforcement learning, (ADPRL)

作者： Jan Peters Jens Kober Department of Empirical Inference and Machine Learning Max-Planck Institute of Biological Cybernetics Tubingen Germany

reinforcement learning is an essential ability for robots to learn new motor skills. Nevertheless, few methods scale into the domain of anthropomorphic robotics. In order to improve in terms of efficiency, the problem is reduced onto reward-weighted imitation. By doing so, we are able to generate a framework for policy learning which both unifies previous reinforcement learning approaches and allows the derivation of novel algorithms. We show our two most relevant applications both for motor primitive learning (e.g., a complex Ball-in-a-Cup task using a real Barrett WAM robot arm) and learning task-space control.

关键词： Robots learning

来源：评论

学校读者我要写书评

暂无评论

Neural-network-based reinforcement learning controller for nonlinear systems with non-symmetric dead-zone inputs

Neural-network-based reinforcement learning controller for n...

引用

ieee symposium on adaptive dynamic programming and reinforcement learning, (ADPRL)

作者： Xin Zhang Huaguang Zhang Derong Liu Yongsu Kim School of Information Science and Engineering Northeastern University Shenyang Liaoning China Department of Electrical and Computer Engineering University of Illinois Chicago Chicago IL USA

A novel adaptive-critic-based NN controller using reinforcement learning is developed for a class of nonlinear systems with non-symmetric dead-zone inputs. The adaptive critic NN controller uses two NNs: the critic NN is used to approximate the strategic utility function, and the output of action NN is used to approximate the unknown nonlinear function and to minimize the strategic utility function. The tuning of the NNs is performed online without an explicit offline learning phase. The uniformly ultimate boundedness of the close-loop tracking error is derived by using using the Lyapunov method. Finally, a numerical example is included to show the effectiveness of the theoretical results.

关键词： learning Nonlinear control systems Control systems Nonlinear systems Neural networks adaptive control Programmable control Lyapunov method Actuators Servomechanisms

来源：评论

学校读者我要写书评

暂无评论

Inferring bounds on the performance of a control policy from a sample of trajectories

Inferring bounds on the performance of a control policy from...

引用

ieee symposium on adaptive dynamic programming and reinforcement learning, (ADPRL)

作者： Raphael Fonteneau Susan Murphy Louis Wehenkel Damien Ernst Department of Electrical Engineering and Computer Science University of Liège Belgium University of Michigan USA

We propose an approach for inferring bounds on the finite-horizon return of a control policy from an off-policy sample of trajectories collecting state transitions, rewards, and control actions. In this paper, the dynamics, control policy, and reward function are supposed to be deterministic and Lipschitz continuous. Under these assumptions, a polynomial algorithm, in terms of the sample size and length of the optimization horizon, is derived to compute these bounds, and their tightness is characterized in terms of the sample density.

关键词： Control systems Computational modeling Polynomials Optimal control dynamic programming Predictive models Fingers Upper bound Biomedical engineering Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Multiagent reinforcement learning in extensive form games with complete information

Multiagent reinforcement learning in extensive form games wi...

引用

ieee symposium on adaptive dynamic programming and reinforcement learning, (ADPRL)

作者： Ali Akramizadeh Mohammad -B. Menhaj Ahmad Afshar Center of Computational Intelligence and Large Scale System EE Department Polytechnic University Iran

Recent developments in multiagent reinforcement learning, mostly concentrate on normal form games or restrictive hierarchical form games. In this paper, we use the well known Q-learning in extensive form games which agents have a fixed priority in action selection. We also introduce a new concept called associative Q-values which not only can be used in action selection, leading to a subgame perfect equilibrium, but also can be used in update rule which is proved to be convergent. Associative Q-values are the expected utility of an agent in a game situation which is an estimate of the value of the subgame perfect equilibrium point.

关键词： Game theory Multiagent systems learning systems Machine learning Utility theory Sensor systems Actuators Robot sensing systems Distributed control Collaboration

来源：评论

学校读者我要写书评

暂无评论

Planning under uncertainty, ensembles of disturbance trees and kernelized discrete action spaces

Planning under uncertainty, ensembles of disturbance trees a...

引用

ieee symposium on adaptive dynamic programming and reinforcement learning, (ADPRL)

作者： Boris Defourny Damien Ernst Louis Wehenkel Department of Electrical Engineering and Computer Science University of Liège Belgium

Optimizing decisions on an ensemble of incomplete disturbance trees and aggregating their first stage decisions has been shown as a promising approach to (model-based) planning under uncertainty in large continuous action spaces and in small discrete ones. The present paper extends this approach and deals with large but highly structured action spaces, through a kernel-based aggregation scheme. The technique is applied to a test problem with a discrete action space of 6561 elements adapted from the NIPS 2005 SensorNetwork benchmark.

关键词： Uncertainty Stochastic processes Application software Benchmark testing Decision making Operations research Large-scale systems Power generation Processor scheduling dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Integrating sporadic imitation in reinforcement learning robots

Integrating sporadic imitation in Reinforcement Learning rob...

引用

ieee symposium on adaptive dynamic programming and reinforcement learning, (ADPRL)

作者： Willi Richert Ulrich Scheller Markus Koch Bernd Kleinjohann Claudius Stern Faculty of of Computer Science Electrical Engineering and Mathematics University of Paderborn Paderborn Germany

Although the combination of reinforcement learning and imitation has been already considered in recent research, it always revolved around fixed settings where demonstrator and imitator are fixed and the imitation process is a well-defined period of time. What is missing is the investigation of approaches that also work in scenarios where imitation is only sporadically possible. This means that in a multi-robot scenario a robot is now allowed to interrupt another robot by asking to repeat certain actions, but can only observe and integrate information bits delivered occasionally. In this paper we present how that can be done in continuous and noisy environment within an SMDP context.

关键词： learning Orbital robotics Space exploration Humans Neurons Educational robots Working environment noise Animals Mirrors Fires

来源：评论

学校读者我要写书评

暂无评论

Iterative local dynamic programming

Iterative local dynamic programming

引用

ieee symposium on adaptive dynamic programming and reinforcement learning, (ADPRL)

作者： Emanuel Todorov Yuval Tassa Department of Cognitive Science University of California San Diego USA Center of Neural Computation Hebrew University of Jerusalem Israel

We develop an iterative local dynamic programming method (iLDP) applicable to stochastic optimal control problems in continuous high-dimensional state and action spaces. Such problems are common in the control of biological movement, but cannot be handled by existing methods. iLDP can be considered a generalization of differential dynamic programming, in as much as: (a) we use general basis functions rather than quadratics to approximate the optimal value function; (b) we introduce a collocation method that dispenses with explicit differentiation of the cost and dynamics and ties iLDP to the unscented Kalman filter; (c) we adapt the local function approximator to the propagated state covariance, thus increasing accuracy at more likely states. Convergence is similar to quasi-Newton methods. We illustrate iLDP on several problems including the ldquoswimmerrdquo dynamical system which has 14 state and 4 control variables.

关键词： dynamic programming Function approximation Optimal control Open loop systems Costs Iterative methods Stochastic processes Control systems Stochastic resonance learning

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103页 << < 78 79 80 81 82 83 84 85 86 87 > >>

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：