Nonlinear control of a boost converter using a robust regression based reinforcement learning algorithm

Pradeep, D. John; Noel, Mathew Mithra; Arun, N.

doi:10.1016/j.engappai.2016.02.007

Cited by 24 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Through continuous interaction with the environment, a learning agent can finally achieve the goal. The concept of reinforcement learning has been proposed as early as the last century [3]. Reinforcement learning is mainly applied to many interactive behaviors and decision-making problems-such as video games, robot control systems, human-computer dialogue, etc, which cannot be well dealt with by the well-known supervised learning and unsupervised learning methods [4][5][6][7].…”

Section: Reinforcement Learningmentioning

confidence: 99%

A Confrontation Decision-Making Method with Deep Reinforcement Learning and Knowledge Transfer for Multi-Agent System

2020

Symmetry

View full text Add to dashboard Cite

In this paper, deep reinforcement learning (DRL) and knowledge transfer are used to achieve the effective control of the learning agent for the confrontation in the multi-agent systems. Firstly, a multi-agent Deep Deterministic Policy Gradient (DDPG) algorithm with parameter sharing is proposed to achieve confrontation decision-making of multi-agent. In the process of training, the information of other agents is introduced to the critic network to improve the strategy of confrontation. The parameter sharing mechanism can reduce the loss of experience storage. In the DDPG algorithm, we use four neural networks to generate real-time action and Q-value function respectively and use a momentum mechanism to optimize the training process to accelerate the convergence rate for the neural network. Secondly, this paper introduces an auxiliary controller using a policy-based reinforcement learning (RL) method to achieve the assistant decision-making for the game agent. In addition, an effective reward function is used to help agents balance losses of enemies and our side. Furthermore, this paper also uses the knowledge transfer method to extend the learning model to more complex scenes and improve the generalization of the proposed confrontation model. Two confrontation decision-making experiments are designed to verify the effectiveness of the proposed method. In a small-scale task scenario, the trained agent can successfully learn to fight with the competitors and achieve a good winning rate. For large-scale confrontation scenarios, the knowledge transfer method can gradually improve the decision-making level of the learning agent.

show abstract

Section: Reinforcement Learningmentioning

confidence: 99%

A Confrontation Decision-Making Method with Deep Reinforcement Learning and Knowledge Transfer for Multi-Agent System

2020

Symmetry

View full text Add to dashboard Cite

show abstract

“…RL agents are generally instructed by instant numerical rewards to approach their optimal behavior . To take some instances, they have been employed for control design in several works …”

Section: Control Designmentioning

confidence: 99%

“…40 To take some instances, they have been employed for control design in several works. [41][42][43] The learning algorithms can be fallen into three categories including supervised, unsupervised, and reinforcement learning (RL). Despite artificial neural network and GA, which have been studied in some of the previous works in active structural control area, RL has not been paid attention to a satisfactory level for the purpose of parameters learning despite having distinctive features.…”

Section: Control Designmentioning

confidence: 99%

Online control of an active seismic system via reinforcement learning

Khalatbarisoltani

Soleymani

Khodadadi

2018

Struct Control Health Monit

View full text Add to dashboard Cite

Summary Tuning the seismic control systems in order to achieve optimal performance is a challenging area due to the system and disturbance uncertainties. Although, model uncertainties, process time delay, and actuator dynamics can be considered as typical uncertainties, the main source of uncertainty in a seismic control system comes from the aleatory nature of earthquake disturbances. In this case, tuning of the control system based on a given seismic record may not necessarily result in optimal performance for other earthquakes. In this paper, a methodological approach is proposed for online control of active structural control systems considering seismic uncertainties. For this purpose, the concept of reinforcement learning is utilized for online tuning of an active mass drive system. The controller comprises a gain‐scheduling fuzzy proportional derivative controller whose gains are tuned via an online reinforcement learning algorithm. Moreover, in order to tackle the time delays, a dynamic state predictor is utilized in conjunction with the proposed controller. To evaluate the performance of proposed controller, according to an assumed site hazard, thousand ground motion records are generated and clustered based on their spectral features using a fuzzy clustering approach. Finally, the controller is implemented in a laboratory‐scale structure, and its performance is examined in the presence of the cluster centers and some real seismic records simulated on a shake table. The test results reveal successful performance of the proposed controller in tackling a wide range of seismic disturbances in the presence of time delay.

show abstract

“…Neste tipo de aprendizagem, temos a realização de um mapeamento entrada-saída através da interação contínua com o ambiente, visando minimizar umíndice escalar de desempenho (Haykin, 2007). RL também tem sido incorporada em diversas técnicas de controle para sistemas lineares tanto na forma de compensação de dinâmica não modelada quanto no ajuste dos parâmetros dos controladores utilizados como nos trabalhos (Brinkmann et al, 2018;Kim et al, 2019;Pradeep et al, 2016;Zhu et al, 2015;Jardine et al, 2019;Yang et al, 2018;Bejar and Moran, 2019). A aprendizagem por reforçoé um subtópico dentro da aprendizagem de máquinas, porém não se assemelha com a aprendizagem supervisionada e não-supervisionada, sendo considerada o terceiro pilar da aprendizagem de máquinas.…”

Section: Introductionunclassified

Linearização por realimentação e aprendizagem por reforço para o controle do sistema de posicionamento do ROV

Cadengue

Fidelis

Lima

et al. 2019

Anais Do 14º Simpósio Brasileiro De Automação Inteligente

View full text Add to dashboard Cite

A ROV (Remotely Operated underwater Vehicle) system needs a precise estimation of its position in order to avoid damage and imprecise movements in certain missions. In this paper, an intelligent controller for the trajectory tracking of a ROV susceptible to external forces (water dynamics, currents, animals, etc.) is proposed based on feedback linearization with an adaptative function optimized using a machine learning strategy. This work proposes an approach to the matter employing an reinforcement learning algorithm, the-greedy, to let him discover for itself an optimal learning rate for the used compensator. Numerical results confirm a strong improvement in the performance of the controller when the proposed compensator and learning strategy is inserted. Resumo: Um sistema ROV (Remotely Operated underwater Vehicle) precisa de uma estimação precisa da sua posição para evitar danos e movimentos imprecisos para certas tarefas. Neste artigo, um controlador inteligente foi proposto para o rastreamento da trajetória de um ROV suscetível a forças externas (dinâmica daágua, correntes, animais, etc.), este controlador foi baseado no método de linearização por realimentação com uma função adaptativa otimizada utilizando uma estratégia de aprendizagem de máquina. Este trabalho propõe o emprego de um algoritmo de aprendizagem por reforço, o-greedy, para o deixar descobrir por si só uma taxa de aprendizagemótima para o compensador. Resultados numéricos confirmam uma forte melhora na performance do controlador quando o compensador proposto e a estratégia de aprendizageḿ e inserida.

show abstract

Nonlinear control of a boost converter using a robust regression based reinforcement learning algorithm

Cited by 24 publications

References 20 publications

A Confrontation Decision-Making Method with Deep Reinforcement Learning and Knowledge Transfer for Multi-Agent System

A Confrontation Decision-Making Method with Deep Reinforcement Learning and Knowledge Transfer for Multi-Agent System

Online control of an active seismic system via reinforcement learning

Linearização por realimentação e aprendizagem por reforço para o controle do sistema de posicionamento do ROV

Contact Info

Product

Resources

About