检索结果-内蒙古大学图书馆

ieee symposium on adaptive dynamic programming and reinforcement learning

作者： Akramizadeh, Ali Menhaj, Mohammad-B. Afshar, Ahmad Polytech Univ Tehran EE Dept Ctr Computat Intelligence & Large Scale Syst Tehran Iran

ISBN: (纸本)9781424427611

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： Multiagent reinforcement learning extensive form game game theory backward induction subgame perfect equilibrium exploration strategies

来源：评论

学校读者我要写书评

暂无评论

Theoretical Analysis of a reinforcement learning based Switching Scheme

Theoretical Analysis of a Reinforcement Learning based Switc...

引用

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

作者： Heydari, Ali South Dakota Sch Mines & Technol Dept Mech Engn Rapid City SD 57701 USA

ISBN: (纸本)9781479945528

A reinforcement learning based scheme for optimal switching with an infinite-horizon cost function is briefly proposed in this paper. Several theoretical questions are shown to arise regarding its convergence, optimality of the result, and continuity of the limit function, to be uniformly approximated using parametric function approximators. The main contribution of the paper is providing rigorous answers for the questions, where, sufficient conditions for convergence, optimality, and continuity are provided.

关键词： function approximation learning (artificial intelligence) infinite-horizon cost function optimal switching parametric function approximators reinforcement learning based switching scheme Approximation methods Artificial neural networks Convergence Cost function Optimal control Schedules Switches learning (artificial intelligence) Cost functions Approximation method function approximation Switches Converge Artificial neural networks Optimal control Theoretical analysis

来源：评论

学校读者我要写书评

暂无评论

adaptive dynamic programming for Finite-Horizon Optimal Control of Discrete-Time Nonlinear Systems with ε-Error Bound

引用

ieee TRANSACTIONS ON NEURAL NETWORKS 2011年第1期22卷 24-36页

作者： Wang, Fei-Yue Jin, Ning Liu, Derong Wei, Qinglai Chinese Acad Sci Inst Automat Key Lab Complex Syst & Intelligence Sci Beijing 100190 Peoples R China Univ Illinois Dept Elect & Comp Engn Chicago IL 60607 USA

In this paper, we study the finite-horizon optimal control problem for discrete-time nonlinear systems using the adaptive dynamic programming (ADP) approach. The idea is to use an iterative ADP algorithm to obtain the optimal control law which makes the performance index function close to the greatest lower bound of all performance indices within an epsilon-error bound. The optimal number of control steps can also be obtained by the proposed ADP algorithms. A convergence analysis of the proposed ADP algorithms in terms of performance index function and control policy is made. In order to facilitate the implementation of the iterative ADP algorithms, neural networks are used for approximating the performance index function, computing the optimal control policy, and modeling the nonlinear system. Finally, two simulation examples are employed to illustrate the applicability of the proposed method.

关键词： adaptive critic designs adaptive dynamic programming approximate dynamic programming learning control neural control neural dynamic programming optimal control reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Neural-Network-Based adaptive dynamic Surface Control for MIMO Systems with Unknown Hysteresis

Neural-Network-Based Adaptive Dynamic Surface Control for MI...

引用

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

作者： Liu, Lei Wang, Zhanshan Shen, Zhengwei Northeastern Univ Coll Informat Sci & Engn Shenyang Liaoning Peoples R China

ISBN: (纸本)9781479945528

This paper focuses on the composite adaptive tracking control for a class of nonlinear multiple-input-multiple-output (MIMO) systems with unknown backlash-like hysteresis nonlinearities. A dynamic surface control method is incorporated into the proposed control strategy to eliminate the problem of explosion of complexity. Compared with some existing methods, the prediction error between system state and serial-parallel estimation model is combined with compensated tracking error to construct the adaptive laws for neural network (NN) weights. It is shown that the proposed control approach can guarantee that all the signals of the resulting closed-loop systems are semi-globally uniformly ultimately bounded and the tracking error converges to a small neighborhood. Finally, simulation results are provided to confirm the effectiveness of the proposed approaches.

关键词： dynamic surface control prediction error backlash-like hysteresis adaptive neural network control

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Partially Observable dynamic Processes Using adaptive dynamic programming

Data-Driven Partially Observable Dynamic Processes Using Ada...

引用

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

作者： Zhong, Xiangnan Ni, Zhen Tang, Yufei He, Haibo Univ Rhode Isl Dept Elect Comp & Biomed Engn Kingston RI 02881 USA

ISBN: (纸本)9781479945528

adaptive dynamic programming (ADP) has been widely recognized as one of the "core methodologies" to achieve optimal control for intelligent systems in Markov decision process (MDP). Generally, ADP control design requires all the information of the system dynamics. However, in many practical situations, the measured input and output data can only represent part of the system states. This means the complete information of the system cannot be available in many real-world cases, which narrows the range of application of the ADP design. In this paper, we propose a data-driven ADP method to stabilize the system with partially observable dynamics based on neural network techniques. A state network is integrated into the typical actor-critic architecture to provide an estimated state from the measured input/output sequences. The theoretical analysis and the stability discussion of this data-driven ADP method are also provided. Two examples are studied to verify our proposed method.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Higher-level application of adaptive dynamic programming/reinforcement learning - A next phase for controls and system identification?

Higher-level application of Adaptive Dynamic Programming/Rei...

引用

ieee symposium on adaptive dynamic programming and reinforcement learning

作者： Lendaris, George G. Systems Science Graduate Program Portland State University Portland OR United States

ISBN: (纸本)9781424498888

In previous work it was shown that adaptive-Critic-type Approximate dynamic programming could be applied in a higher-level way to create autonomous agents capable of using experience to discern context and select optimal, context-dependent control policies. Early experiments with this approach were based on full a priori knowledge of the system being monitored. The experiments reported in this paper, using small neural networks representing families of mappings, were designed to explore what happens when knowledge of the system is less precise. Results of these experiments show that agents trained with this approach perform well when subject to even large amounts of noise or when employing (slightly) imperfect models. The results also suggest that aspects of this method of context discernment are consistent with our intuition about human learning. The insights gained from these explorations can be used to guide further efforts for developing this approach into a general methodology for solving arbitrary identification and control problems. © 2011 ieee.

关键词： reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Optimal Consensus Control for Discrete-Time Multi-Agent Systems With Unknown dynamics Using reinforcement learning Method

引用

ieee TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2017年第5期64卷 4091-4100页

作者： Zhang, Huaguang Jiang, He Luo, Yanhong Xiao, Geyang Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China

This paper investigates the optimal consensus control problem for discrete-time multi-agent systems with completely unknown dynamics by utilizing a data-driven reinforcement learning method. It is known that the optimal consensus control for multi-agent systems relies on the solution of the coupled Hamilton-Jacobi-Bellman equation, which is generally impossible to be solved analytically. Even worse, most real-world systems are too complicated to obtain accurate mathematical models. To overcome these deficiencies, a data-based adaptive dynamic programming method is presented using the current and past system data rather than the accurate system models also instead of the traditional identification scheme which would cause the approximation residual errors. First, we establish a discounted performance index and formulate the optimal consensus problem via Bellman optimality principle. Then, we introduce the policy iteration algorithm which motivates this paper. To implement the proposed online action-dependent heuristic dynamic programming method, two neural networks (NNs), 1) critic NN and 2) actor NN, are employed to approximate the iterative performance index functions and control policies, respectively, in real time. Finally, two simulation examples are provided to demonstrate the effectiveness of the proposed method.

关键词： Action-dependent heuristic dynamic programming (ADHDP) adaptive dynamic programming (ADP) data-driven multi-agent systems optimal consensus control reinforcement learning (RL)

来源：评论

学校读者我要写书评

暂无评论

Model-free Q-learning over Finite Horizon for Uncertain Linear Continuous-time Systems

Model-free <i>Q</i>-learning over Finite Horizon for Uncerta...

引用

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

作者： Xu, Hao Jagannathan, S. Texas A&M Univ Coll Sci & Engn Corpus Christi TX 78412 USA Missouri Univ Sci & Technol Dept Elect & Comp Engn Rolla MO USA

ISBN: (纸本)9781479945528

In this paper, a novel optimal control over finite horizon has been introduced for linear continuous-time systems by using adaptive dynamic programming (ADP). First, a new time-varying Q-function parameterization and its estimator are introduced. Subsequently, Q-function estimator is tuned online by using both Bellman equation in integral form and terminal cost. Eventually, near optimal control gain is obtained by using the Q-function estimator. All the closed-loop signals are shown to be bounded by using Lyapunov stability analysis where bounds are functions of initial conditions and final time while the estimated control signal converges close to the optimal value. The simulation results illustrate the effectiveness of the proposed scheme.

关键词： adaptive dynamics programming (ADP) Q-learning Optimal Control Riccati Equation Forward-in-time

来源：评论

学校读者我要写书评

暂无评论

Continuous-Time Differential dynamic programming with Terminal Constraints

Continuous-Time Differential Dynamic Programming with Termin...

引用

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

作者： Sun, Wei Theodorou, Evangelos A. Tsiotras, Panagiotis

ISBN: (纸本)9781479945528

In this work, we revisit the continuous-time Differential dynamic programming (DDP) approach for solving optimal control problems with terminal state constraints. We derive two algorithms, each for different order of expansion of the system dynamics and we investigate their performance in terms of their convergence speed. Compared to previous work, we provide a set of backward differential equations for the value function expansion by relaxing the assumption that the initial nominal control must be very close to the optimal control solution. We apply the derived algorithms to two classical optimal control problems, namely, the inverted pendulum and the Dreyfus rocket problem and show the benefit of second order expansion.

关键词： Inverted pendulum

来源：评论

学校读者我要写书评

暂无评论

Nonparametric Infinite Horizon Kullback-Leibler Stochastic Control

Nonparametric Infinite Horizon Kullback-Leibler Stochastic C...

引用

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

作者： Pan, Yunpeng Theodorou, Evangelos A. Georgia Inst Technol Daniel Guggenheim Sch Aerosp Engn Atlanta GA 30332 USA

ISBN: (纸本)9781479945528

We present two nonparametric approaches to Kullback-Leibler (KL) control, or linearly-solvable Markov decision problem (LMDP) based on Gaussian processes (GP) and Nystrom approximation. Compared to recently developed parametric methods, the proposed data-driven frameworks feature accurate function approximation and efficient on-line operations. Theoretically, we derive the mathematical connection of KL control based on dynamic programming with earlier work in control theory which relies on information theoretic dualities for the infinite time horizon case. Algorithmically, we give explicit optimal control policies in nonparametric forms, and propose on-line update schemes with budgeted computational costs. Numerical results demonstrate the effectiveness and usefulness of the proposed frameworks.

关键词： dynamic programming

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：