检索结果-内蒙古大学图书馆

Self-learning Control Using Dual Heuristic programming with Global Laplacian Eigenmaps

ieee TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2017年第12期64卷 9517-9526页

作者： Xu, Xin Yang, Huiyuan Lian, Chuanqiang Liu, Jiahang Natl Univ Def Technol Inst Unmanned Syst Coll Intelligence Sci Changsha 410073 Hunan Peoples R China

In this paper, to solve nonlinear optimal control problems which can be modeled as Markov decision processes (MDPs), we present an online self-learning control algorithm called dual heuristic programming with global Laplacian Eigenmaps (GLEM-DHP). The GLEM-DHP algorithm makes use of GLEM, which is an improved manifold learning approach with global information, to learn the features for value function approximation of the MDP. Different from traditional feature representation methods using neural networks, the manifold-based features can be learned before the online learning process by collecting samples from the MDP. More importantly, in addition to local features, global information can also be utilized by using the geodesic minimum spanning tree (GMST) approach. Based on the theoretical property of GMST, it is shown that the GLEM-based features can represent the intrinsic geometric property of MDP states, which is beneficial to improve the performance of value function approximation and, hence, leads to better learning control properties. To compare the proposed method with previous learning control algorithms, the performance of GLEM-DHP is evaluated on two nonlinear control problems, which include the cart-pole problem and the ball-plate control problem. Simulation and experimental results show that the GLEM-DHP algorithm can obtain better learning control performance than previous learning control algorithms with manually designed features, as well as manifold features only with local information.

关键词： adaptive critic designs (ACD) approximate dynamic programming (ADP) Laplacian Eigenmaps (LEs) manifold learning reinforcement learning (RL)

来源：评论

学校读者我要写书评

暂无评论

Evaluation of policy gradient methods and variants on the cart-pole benchmark

Evaluation of policy gradient methods and variants on the ca...

引用

ieee International symposium on Approximate dynamic programming and reinforcement learning

作者： Riedmiller, Martin Peters, Jan Schaal, Stefan Univ Osnabruck Neuroinformat Grp D-4500 Osnabruck Germany Univ Southern Calif Computat Learning & Motor Control Los Angeles CA 90007 USA

ISBN: (纸本)9781424407064

In this paper, we evaluate different versions from the three main kinds of model-free policy gradient methods, i.e., finite difference gradients, 'vanilla' policy gradients and natural policy gradients. Each of these methods is first presented in its simple form and subsequently refined and optimized. By carrying out numerous experiments on the cart pole regulator benchmark we aim to provide a useful baseline for future research on parameterized policy search algorithms. Portable C++ code is provided for both plant and algorithms;thus, the results in this paper can be reevaluated, reused and new algorithms can be inserted with ease.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

An Online reinforcement learning Wing-Tracking Mechanism for Flexible Wing Aircraft 13

An Online Reinforcement Learning Wing-Tracking Mechanism for...

引用

13th ieee International symposium on Robotic and Sensors Environments (ROSE)

作者： Abouheaf, Mohammed Mailhot, Nathaniel Gueaieb, Wail Univ Ottawa Sch Elect Engn & Comp Sci Ottawa ON Canada Aswan Univ Coll Energy Engn Aswan Egypt Univ Ottawa Dept Mech Engn Ottawa ON Canada

ISBN: (纸本)9781728119649

Flexible wing aircraft are gaining an increasing interest due to their salient features, such as inexpensive market price, low-cost operation, in-flight robustness, multi-purpose use, and their ability to operate with very little infrastructure. The continuous variations in the aerodynamics of the wing and additionally the kinematic and dynamic constraints that evolve due to the wing-fuselage interactions make the modeling task of such systems ultimately challenging. An online model-free adaptive control mechanism based on two linear actuation systems is proposed in this manuscript to fulfill different pitch-roll maneuvers. The mechanism employs model-free tracking control strategies and utilizes a real-time value iteration-based reinforcement learning process. The adaptation of the control gains is accomplished online using means of adaptive critics.

关键词： Mathematical model Adaptation models Aerodynamics Aircraft Atmospheric modeling adaptive learning reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

learning to Regulate Rolling Ball Motion

Learning to Regulate Rolling Ball Motion

引用

ieee symposium Series on Computational Intelligence (ieee SSCI)

作者： Jha, Devesh K. Yerazunis, William Nikovski, Daniel Farahmand, Amir-massoud Mitsubishi Elect Res Labs Cambridge MA 02139 USA

ISBN: (纸本)9781538627266

In this paper, we present a problem of regulating the motion of a rolling ball in a one-dimensional space in the presence of non-linear effects of friction and contact. The regulation problem is solved using a model-based reinforcement learning technique. A Gaussian process model is learned to make predictions on the motion of the ball and then, the predictive model is used to solve for the control policy using dynamic programming by estimating the value functions. Several results are shown to demonstrate the simple, yet interesting motion dynamics for the ball. Our hope is that the proposed system will serve as a simple benchmark system for reinforcement and robot learning.

关键词： reinforcement learning Gaussian Process Position Regulation

来源：评论

学校读者我要写书评

暂无评论

Annealing-Pareto Multi-Objective Multi-Armed Bandit Algorithm

Annealing-Pareto Multi-Objective Multi-Armed Bandit Algorith...

引用

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

作者： Yahyaa, Saba Q. Drugan, Madalina M. Manderick, Bernard Vrije Univ Brussel Dept Comp Sci Pl Laan 2 B-1050 Brussels Belgium

ISBN: (纸本)9781479945528

In the stochastic multi-objective multi-armed bandit (or MOMAB), arms generate a vector of stochastic rewards, one per objective, instead of a single scalar reward. As a result, there is not only one optimal arm, but there is a set of optimal arms (Pareto front) of reward vectors using the Pareto dominance relation and there is a trade-off between finding the optimal arm set (exploration) and selecting fairly or evenly the optimal arms (exploitation). To trade-off between exploration and exploitation, either Pareto knowledge gradient (or Pareto-KG for short), or Pareto upper confidence bound (or Pareto-UCB1 for short) can be used. They combine the KG-policy and UCB1-policy, respectively with the Pareto dominance relation. In this paper, we propose Pareto Thompson sampling that uses Pareto dominance relation to find the Pareto front. We also propose annealing-Pareto algorithm that trades-off between the exploration and exploitation by using a decaying parameter epsilon(t) in combination with Pareto dominance relation. The annealing-Pareto algorithm uses the decaying parameter to explore the Pareto optimal arms and uses Pareto dominance relation to exploit the Pareto front. We experimentally compare Pareto-KG, Pareto-UCB1, Pareto Thompson sampling and the annealing-Pareto algorithms on multi-objective Bernoulli distribution problems and we conclude that the annealing-Pareto is the best performing algorithm.

关键词： Pareto optimisation sampling methods simulated annealing stochastic programming KG-policy MOMAB Pareto Thompson sampling Pareto dominance relation Pareto front Pareto knowledge gradient Pareto optimal arms Pareto upper confidence bound Pareto-KG Pareto-UCB1 UCB1-policy annealing-Pareto multiobjective multiarmed bandit algorithm decaying parameter multiobjective Bernoulli distribution problems multiobjective multiarmed bandit reward vectors stochastic rewards Annealing Entropy Heuristic algorithms Nickel Pareto optimization Probability distribution Vectors Pareto optimisation Heuristic algorithms Probability distribution sampling methods simulated annealing Arm spiral arm entropy Exploration Nickel annealing Arms stochastic programming Stochastic models Cloning Vectors

来源：评论

学校读者我要写书评

暂无评论

Intelligent Energy Management Strategy Based on an Improved reinforcement learning Algorithm With Exploration Factor for a Plug-in PHEV

引用

ieee TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第7期23卷 8725-8735页

作者： Lin, Xinyou Zhou, Kuncheng Mo, Liping Li, Hailin Fuzhou Univ Coll Mech Engn & Automat Fuzhou 350108 Peoples R China West Virginia Univ Dept Mech & Aerosp Engn Morgantown WV 26506 USA

An intelligent energy management strategy (EMS) based on an improved reinforcement learning (RL) algorithm is developed to enhance the adaptability of the EMS and to further improve the fuel efficiency of a Plug-in Parallel Hybrid Electric Vehicle (PHEV). Both the numerical model and the energy management strategy of a plug-in PHEV are described. The improved RL with Q-learning algorithm is implemented to acquire the optimal control strategies for improving fuel economy. The Markov Chain is employed to calculate the Transition Probability Matrix of the required power. A Kullback-Leibler (KL) divergence rate is designed to activate the update of EMS, when a new corresponding driving cycle is expected. An Exploration Factor (FT) is proposed to overcome the disadvantages of the normal RL algorithm in convergence rate and reward cost evaluation. The diverse KL divergence rates are examined to seek optimal solutions. The normal-RI, strategy, rule-based strategy, and dynamic programming strategy are implemented as benchmark strategies to verify the effectiveness of the proposed strategy. The validation results indicate that the improved RL algorithm with FY makes it possible to promote the EMS capable of significantly improving the energy efficiency of a plug-in PHEV.

关键词： Hybrid electric vehicle energy management strategy reinforcement learning algorithm self-adaptive exploration factor

来源：评论

学校读者我要写书评

暂无评论

Short-term stock market timing prediction under reinforcement learning schemes

Short-term stock market timing prediction under reinforcemen...

引用

2007 ieee symposium on Approximate dynamic programming and reinforcement learning, ADPRL 2007

作者： Hailin, Li Dagli, Cihan H. Enke, David Department of Engineering Management and Systems Engineering University of Missouri-Rolla Rolla MO 65409-0370 United States

ISBN: (纸本)1424407060

There are fundamental difficulties when only using a supervised learning philosophy to predict financial stock short-term movements. We present a reinforcement-oriented forecasting framework in which the solution is converted from a typical error-based learning approach to a goal-directed matchbased learning method. The real market timing ability in forecasting is addressed as well as traditional goodness-of-fit-based criteria. We develop two applicable hybrid prediction systems by adopting actor-only and actor-critic reinforcement learning, respectively, and compare them to both a supervised-only model and a classical random walk benchmark in forecasting three daily-based stock indices series within a 21-year learning and testing period. The performance of actor-critic-based systems was demonstrated to be superior to that of other alternatives, while the proposed actor-only systems also showed efficacy. © 2007 ieee.

关键词： reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

reinforcement learning for adaptive Periodic Linear Quadratic Control 58

Reinforcement Learning for Adaptive Periodic Linear Quadrati...

引用

58th ieee Conference on Decision and Control (CDC)

作者： Pang, Bo Jiang, Zhong-Ping Mareels, Iven NYU Tandon Sch Engn Dept Elect & Comp Engn Control & Networks LabMetrotech Ctr 6 Brooklyn NY 11201 USA IBM Res Australia Melbourne Vic 3006 Australia

ISBN: (纸本)9781728113982

This paper presents a first solution to the problem of adaptive LQR for continuous-time linear periodic systems. Specifically, reinforcement learning and adaptive dynamic programming (ADP) techniques are used to develop two algorithms to obtain near-optimal controllers. Firstly, the policy iteration (PI) and value iteration (VI) methods are proposed when the model is known. Then, PI-based and VI-based off-policy ADP algorithms are derived to find near-optimal solutions directly from input/state data collected along the system trajectories, without the exact knowledge of system dynamics. The effectiveness of the derived algorithms is validated using the well-known lossy Mathieu equation.

关键词： reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Approximate dynamic programming Solutions of Multi-Agent Graphical Games Using Actor-Critic Network Structures

Approximate Dynamic Programming Solutions of Multi-Agent Gra...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Abouheaf, Mohammed I. Lewis, Frank L. Univ Texas Arlington Res Inst Ft Worth TX 76118 USA

ISBN: (纸本)9781467361293;9781467361286

This paper studies a new class of multi-agent discrete-time dynamical graphical games, where interactions between agents are restricted by a communication graph structure. The paper brings together discrete Hamiltonian mechanics, optimal control theory, cooperative control, game theory, reinforcement learning, and neural network structures to solve the multi-agent dynamical graphical games. Graphical game Bellman equations are derived and shown to be equivalent to certain graphical game Hamilton Jacobi Bellman equations developed herein. reinforcement learning techniques are used to solve these dynamical graphical games. Heuristic dynamic programming and Dual Heuristic programming, are extended to solve the graphical games using only neighborhood information. Online adaptive learning structure is implemented using actor-critic networks to solve these graphical games.

关键词： discrete time systems dynamic programming game theory graph theory learning (artificial intelligence) multi-robot systems optimal control

来源：评论

学校读者我要写书评

暂无评论

Disturbance-Aware Neuro-Optimal System Control Using Generative Adversarial Control Networks

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND learning SYSTEMS 2021年第10期32卷 4565-4576页

作者： Chu, Kai-Fung Lam, Albert Y. S. Fan, Chenchen Li, Victor O. K. Univ Hong Kong Dept Elect & Elect Engn Hong Kong Peoples R China Univ Hong Kong Shenzhen Inst Res & Innovat Hong Kong Peoples R China Fano Labs Hong Kong Peoples R China Univ Hong Kong Dept Mech Engn Hong Kong Peoples R China

Disturbance, which is generally unknown to the controller, is unavoidable in real-world systems and it may affect the expected system state and output. Existing control methods, like robust model predictive control, can produce robust solutions to maintain the system stability. However, these robust methods trade the solution optimality for stability. In this article, a method called generative adversarial control networks (GACNs) is proposed to train a controller via demonstrations of the optimal controller. By formulating the optimal control problem in the presence of disturbance, the controller trained by GACNs obtains neuro-optimal solutions without knowing the future disturbance and determines the objective function explicitly. A joint loss, composed of the adversarial loss and the least square loss, is designed to be used in the training of the generator. Experimental results on simulated systems with disturbance show that GACNs outperform other compared control methods.

关键词： Robustness Gallium nitride Optimal control Generators Training dynamic programming adaptive dynamic programming (DP) approximate dynamic programming (ADP) generative adversarial networks (GANs) inverse reinforcement learning (RL) neural networks optimal control

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：