检索结果-内蒙古大学图书馆

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

作者： Zhen Ni Xiao Fang Haibo He Dongbin Zhao Xin Xu Department of Electrical University of Rhode Island Kingston RI USA Institute of Automation Chinese Academy of Sciences Beijing China Institute of Automation National University of Defense Technology Changsha China

In this paper, we proposed a new nonlinear tracking controller based on heuristic dynamic programming (HDP) with the tracking filter. Specifically, we integrate a goal network into the regular HDP design and provide the critic network with detailed internal reward signal to help the value function approximation. The architecture is explicitly explained with the tracking filter, goal network, critic network and action network, respectively. We provide the stability analysis of our proposed controller with Lyapunov approach. It is shown that the filtered tracking errors and the weights estimation errors in neural networks are all uniformly ultimately bounded (UUB) under certain conditions. Finally, we compare our proposed approach with regular HDP approach in virtual reality (VR)/Simulink environment to justify the improved control performance.

关键词： dynamic programming Stability analysis Function approximation Nonlinear systems Vectors Computer architecture Neural networks

来源：评论

学校读者我要写书评

暂无评论

reinforcement learning in the game of Othello: learning against a fixed opponent and learning from self-play

Reinforcement learning in the game of Othello: Learning agai...

引用

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

作者： Michiel van der Ree Marco Wiering Faculty of Mathematics and Natural Sciences University of Groningen Institute of Artificial Intelligence and Cognitive Engineering The Netherlands

This paper compares three strategies in using reinforcement learning algorithms to let an artificial agent learn to play the game of Othello. The three strategies that are compared are: learning by self-play, learning from playing against a fixed opponent, and learning from playing against a fixed opponent while learning from the opponent's moves as well. These issues are considered for the algorithms Q-learning, Sarsa and TD-learning. These three reinforcement learning algorithms are combined with multi-layer perceptrons and trained and tested against three fixed opponents. It is found that the best strategy of learning differs per algorithm. Q-learning and Sarsa perform best when trained against the fixed opponent they are also tested against, whereas TD-learning performs best when trained through self-play. Surprisingly, Q-learning and Sarsa outperform TD-learning against the stronger fixed opponents, when all methods use their best strategy. learning from the opponent's moves as well leads to worse results compared to learning only from the learning agent's own moves.

关键词： Games Training learning (artificial intelligence) Artificial neural networks Heuristic algorithms Testing

来源：评论

学校读者我要写书评

暂无评论

reinforcement learning algorithms for solving classification problems

Reinforcement learning algorithms for solving classification...

引用

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

作者： Marco A. Wiering Hado van Hasselt Auke-Dirk Pietersma Lambert Schomaker Department of Artificial Intelligence University of Groningam Netherlands Multi-agent and Adaptive Computation Centrum Wiskunde and Informatica Netherlands

We describe a new framework for applying reinforcement learning (RL) algorithms to solve classification tasks by letting an agent act on the inputs and learn value functions. This paper describes how classification problems can be modeled using classification Markov decision processes and introduces the Max-Min ACLA algorithm, an extension of the novel RL algorithm called actor-critic learning automaton (ACLA). Experiments are performed using 8 datasets from the UCI repository, where our RL method is combined with multi-layer perceptrons that serve as function approximators. The RL method is compared to conventional multi-layer perceptrons and support vector machines and the results show that our method slightly outperforms the multi-layer perceptron and performs equally well as the support vector machine. Finally, many possible extensions are described to our basic method, so that much future research can be done to make the proposed method even better.

关键词： Training Markov processes Support vector machines learning Testing Artificial neural networks Accuracy

来源：评论

学校读者我要写书评

暂无评论

Self-learning Cruise Control Using Kernel-Based Least Squares Policy Iteration

引用

ieee TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY 2014年第3期22卷 1078-1087页

作者： Wang, Jian Xu, Xin Liu, Daxue Sun, Zhenping Chen, Qingyang Natl Univ Def Technol Coll Mechatron & Automat Changsha 410073 Hunan Peoples R China

This paper presents a novel learning-based cruise controller for autonomous land vehicles (ALVs) with unknown dynamics and external disturbances. The learning controller consists of a time-varying proportional-integral (PI) module and an actor-critic learning control module with kernel machines. The learning objective for the cruise control is to make the vehicle's longitudinal velocity follow a smoothed spline-based speed profile with the smallest possible errors. The parameters in the PI module are adaptively tuned based on the vehicle's state and the action policy of the learning control module. Based on the state transition data of the vehicle controlled by various initial policies, the action policy of the learning control module is optimized by kernel-based least squares policy iteration (KLSPI) in an offline way. The effectiveness of the proposed controller was tested on an ALV platform during long-distance driving in urban traffic and autonomous driving on off-road terrain. The experimental results of the cruise control show that the learning control method can realize data-driven controller design and optimization based on KLSPI and that the controller's performance is adaptive to different road conditions.

关键词： Approximate dynamic programming (ADP) autonomous land vehicle (ALV) cruise control kernel-based least squares policy iteration (KLSPI) reinforcement learning speed control

来源：评论

学校读者我要写书评

暂无评论

A reinforcement learning algorithm developed to model GenCo strategic bidding behavior in multidimensional and continuous state and action spaces

A reinforcement learning algorithm developed to model GenCo ...

引用

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

作者： Alfred Yong Fu Lau Dipti Srinivasan Thomas Reindl National University of Singapore Singapore SG Department of Electrical Computer Engineering National University of Singapore Singapore Solar Energy Research Institute of Singapore National University of Singapore Singapore

The electricity market has provided a complex economic environment, and consequently has increased the requirement for advancement of learning methods. In the agent-based modeling and simulation framework of this economic system, the generation company's decision-making is modeled using reinforcement learning. Existing learning methods that model the generation company's strategic bidding behavior are not adapted to the non-stationary and non-Markovian environment involving multidimensional and continuous state and action spaces. This paper proposes a reinforcement learning method to overcome these limitations. The proposed method discovers the input space structure through the self-organizing map, exploits learned experience through Roth-Erev reinforcement learning and explores through the actor critic map. Simulation results from experiments show that the proposed method outperforms Simulated Annealing Q-learning and Variant Roth-Erev reinforcement learning. The proposed method is a step towards more realistic agent learning in Agent-based Computational Economics.

关键词： learning (artificial intelligence) Electricity supply industry Adaptation models Vectors Computational modeling Simulated annealing Schedules

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

Optimistic planning for continuous-action deterministic systems

Optimistic planning for continuous-action deterministic syst...

引用

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

作者： Lucian Buşoniu Alexander Daniels Rémi Munos Robert Babuška Department of Automation Technical University of Cluj-Napoca Romania France DCSC Delft University of Technology the Netherlands Team SequeL INRIA Lille-Nord Europe France

We consider the class of online planning algorithms for optimal control, which compared to dynamic programming are relatively unaffected by large state dimensionality. We introduce a novel planning algorithm called SOOP that works for deterministic systems with continuous states and actions. SOOP is the first method to explore the true solution space, consisting of infinite sequences of continuous actions, without requiring knowledge about the smoothness of the system. SOOP can be used parameter-free at the cost of more model calls, but we also propose a more practical variant tuned by a parameter α, which balances finer discretization with longer planning horizons. Experiments on three problems show SOOP reliably ranks among the best algorithms, fully dominating competing methods when the problem requires both long horizons and fine discretization.

关键词： Planning Upper bound Optimization dynamic programming Measurement Heuristic algorithms Aerospace electronics

来源：评论

学校读者我要写书评

暂无评论

reinforcement learning to train Ms. Pac-Man using higher-order action-relative inputs

Reinforcement learning to train Ms. Pac-Man using higher-ord...

引用

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

作者： Luuk Bom Ruud Henken Marco Wiering Faculty of Mathematics and Natural Sciences University of Groningen The Netherlands

reinforcement learning algorithms enable an agent to optimize its behavior from interacting with a specific environment. Although some very successful applications of reinforcement learning algorithms have been developed, it is still an open research question how to scale up to large dynamic environments. In this paper we will study the use of reinforcement learning on the popular arcade video game Ms. Pac-Man. In order to let Ms. Pac-Man quickly learn, we designed particular smart feature extraction algorithms that produce higher-order inputs from the game-state. These inputs are then given to a neural network that is trained using Q-learning. We constructed higher-order features which are relative to the action of Ms. Pac-Man. These relative inputs are then given to a single neural network which sequentially propagates the action-relative inputs to obtain the different Q-values of different actions. The experimental results show that this approach allows the use of only 7 input units in the neural network, while still quickly obtaining very good playing behavior. Furthermore, the experiments show that our approach enables Ms. Pac-Man to successfully transfer its learned policy to a different maze on which it was not trained before.

关键词： Games learning (artificial intelligence) Biological neural networks Neurons Heuristic algorithms Training

来源：评论

学校读者我要写书评

暂无评论

Delayed insertion and rule effect moderation of domain knowledge for reinforcement learning

Delayed insertion and rule effect moderation of domain knowl...

引用

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

作者： Teck-Hou Teng Ah-Hwee Tan School of Computer Engineering Center for Computational Intelligence School of Computer Engineering Nanyang Technological University

Though not a fundamental pre-requisite to efficient machine learning, insertion of domain knowledge into adaptive virtual agent is nonetheless known to improve learning efficiency and reduce model complexity. Conventionally, domain knowledge is inserted prior to learning. Despite being effective, such approach may not always be feasible. Firstly, the effect of domain knowledge is assumed and can be inaccurate. Also, domain knowledge may not be available prior to learning. In addition, the insertion of domain knowledge can frame learning and hamper the discovery of more effective knowledge. Therefore, this work advances the use of domain knowledge by proposing to delay the insertion and moderate the effect of domain knowledge to reduce the framing effect while still benefiting from the use of domain knowledge. Using a non-trivial pursuit-evasion problem domain, experiments are first conducted to illustrate the impact of domain knowledge with different degrees of truth. The next set of experiments illustrates how delayed insertion of such domain knowledge can impact learning. The final set of experiments is conducted to illustrate how delaying the insertion and moderating the assumed effect of domain knowledge can ensure the robustness and versatility of reinforcement learning.

关键词： Vectors Knowledge engineering learning (artificial intelligence) Adaptation models Educational institutions Computational modeling Neural networks

来源：评论

学校读者我要写书评

暂无评论

Particle Swarn Optimized adaptive dynamic programming

Particle Swarn Optimized Adaptive Dynamic Programming

引用

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

作者： Dongbin Zhao Jianqiang Yi Derong Liu Key Laboratory of Complex Systems and Intelligence Science Institute of Automation Chinese Academy and Sciences Beijing China Department of Electrical and Computer Engineering University of Illinois Chicago Chicago IL USA

Particle swarm optimization is used for the training of the action network and critic network of the adaptive dynamic programming approach. The typical structures of the adaptive dynamic programming and particle swarm optimization are adopted for comparison to other learning algorithms such as gradient descent method. Besides simulation on the balancing of a cart pole plant, a more complex plant pendulum robot (pendubot) is tested for the learning performance. Compared to traditional adaptive dynamic programming approaches, the proposed evolutionary learning strategy is verified as faster convergence and higher efficiency. Furthermore, the structure becomes simple because the plant model does not need to be identified beforehand

关键词： dynamic programming Particle swarm optimization Neural networks Robots Backpropagation adaptive systems Evolutionary computation learning Cost function Testing

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：