Reinforcement learning for control: Performance, stability, and deep approximators
Reinforcement learning (RL) offers powerful algorithms to search for optimal controllers of
systems with nonlinear, possibly stochastic dynamics that are unknown or highly uncertain …
systems with nonlinear, possibly stochastic dynamics that are unknown or highly uncertain …
On the sample complexity of the linear quadratic regulator
This paper addresses the optimal control problem known as the linear quadratic regulator in
the case when the dynamics are unknown. We propose a multistage procedure, called …
the case when the dynamics are unknown. We propose a multistage procedure, called …
An approximate neuro-optimal solution of discounted guaranteed cost control design
The adaptive optimal feedback stabilization is investigated in this article for discounted
guaranteed cost control of uncertain nonlinear dynamical systems. Via theoretical analysis …
guaranteed cost control of uncertain nonlinear dynamical systems. Via theoretical analysis …
Optimal tracking control of nonlinear multiagent systems using internal reinforce Q-learning
In this article, a novel reinforcement learning (RL) method is developed to solve the optimal
tracking control problem of unknown nonlinear multiagent systems (MASs). Different from …
tracking control problem of unknown nonlinear multiagent systems (MASs). Different from …
Deep reinforcement learning approaches for process control
SPK Spielberg, RB Gopaluni… - 2017 6th international …, 2017 - ieeexplore.ieee.org
In this work, we have extended the current success of deep learning and reinforcement
learning to process control problems. We have shown that if reward hypothesis functions are …
learning to process control problems. We have shown that if reward hypothesis functions are …
Actor-critic reinforcement learning for control with stability guarantee
Reinforcement Learning (RL) and its integration with deep learning have achieved
impressive performance in various robotic control tasks, ranging from motion planning and …
impressive performance in various robotic control tasks, ranging from motion planning and …
Offline and online adaptive critic control designs with stability guarantee through value iteration
This article is concerned with the stability of the closed-loop system using various control
policies generated by value iteration. Some stability properties involving admissibility …
policies generated by value iteration. Some stability properties involving admissibility …
Output feedback Q-learning for discrete-time linear zero-sum games with application to the H-infinity control
Approximate dynamic programming techniques usually rely on the feedback of the
measurement of the complete state, which is generally not available in practical situations. In …
measurement of the complete state, which is generally not available in practical situations. In …
Input–output data-based output antisynchronization control of multiagent systems using reinforcement learning approach
This article investigates an output antisynchronization problem of multiagent systems by
using an input-output data-based reinforcement learning approach. Till now, most of the …
using an input-output data-based reinforcement learning approach. Till now, most of the …
Machine learning in event-triggered control: Recent advances and open issues
Networked control systems have gained considerable attention over the last decade as a
result of the trend towards decentralised control applications and the emergence of cyber …
result of the trend towards decentralised control applications and the emergence of cyber …