Adaptive Dynamic Programming: An Introduction

By Fei-Yue Wang, Huaguang Zhang, Derong Liu. IEEE Computational Intelligence Magazine, 2009

869 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/0e644048852d0a1e0695c33c29f1978f5155a93f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Electrical and Electronic Engineering

Citations in the corpus

Reinforcement Learning in Continuous State and Action Spaces (2012, background): “There is significant overlap between some of the policy-gradient ideas in this section and many of the ideas in the related field of adaptive dynamic programming (ADP) (Powell, 2007; Wang et al, 2009).”
Linear Quadratic Tracking Control of Partially-Unknown Continuous-Time Systems Using Reinforcement Learning (2014, background): “Since there is a strong connection between RL and optimal control [7], [8], a recent objective of control system researchers is to introduce and”
Reinforcement Learning for Partially Observable Dynamic Processes: Adaptive Dynamic Programming Using Measured Output Data (2011, background): “In view of the advantages offered by RL methods, a recent objective of control system researchers is to introduce and develop RL techniques that result in optimal feedback controllers for dynamical systems that can be described in terms of ordinary differential equations [4], [30], [38], [41], [42].”
Online adaptive optimal control for continuous-time Markov jump linear systems using a novel policy iteration algorithm (2015, neutral): “Over the past few decades, Reinforcement Learning (RL) and Approximate/Adaptive Dynamic Programming (ADP) have been widely applied for solving the optimal control problems for linear/nonlinear systems with unknown or uncertain parametric models [41].”
Leader-Based Optimal Coordination Control for the Consensus Problem of Multiagent Differential Games via Fuzzy Adaptive Dynamic Programming (2015, background): “The excellent overview of the state-of-the-art developments of the ADP algorithm has been presented in [25]–[28].”
Optimal control of unknown nonaffine nonlinear discrete-time systems based on adaptive dynamic programming (2012, methodology): “There are several synonyms used for ADP including ‘‘adaptive dynamic programming’’ (Lewis & Vrabie, 2009; Liu & Jin, 2008; Murray, Cox, Lendaris, & Saeks, 2002; Wang et al., 2009), ‘‘approximate dynamic programming’’ (Al-Tamimi et al.”
Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics (2012, background): “See, for example, Lewis and Vrabie (2009) and Wang, Zhang, and Liu (2009) for two review papers, and Al-Tamimi, Lewis, and Abu-Khalaf (2017), Bhasin, Sharma, Patre, and Dixon (2017), Dierks and Jagannathan (2018), Doya (2000), Ferrari, Steck, and Chandramohan (2008), Jiang and Jiang (2017),…”
Near-Optimal Control for Nonzero-Sum Differential Games of Continuous-Time Nonlinear Systems Using Single-Network ADP (2013, methodology): “As an effective intelligent control method to solve optimal control problems forward in time, in recent years, adaptive dynamic programming (ADP) and the related research have played an important role and gained much attention from researchers [7]– [9].”
An Equivalence Between Adaptive Dynamic Programming With a Critic and Backpropagation Through Time (2013, methodology): “A DAPTIVE Dynamic Programming (ADP) [1] is the study of how an agent can learn actions that minimize a long-term cost function.”
Decentralized Stabilization for a Class of Continuous-Time Nonlinear Interconnected Systems Using Online Learning Optimal Control Approach (2014, neutral): “Then, we should put our emphasis on solving the HJB equations, which yet, is regarded as a difficult task [12], [13].”
A visual analytics approach to understanding cycling behaviour (2012, neutral): “Nonetheless, the predicted breakup time of 1.85 t sh is located within the proposed boundaries given by Pilch and Erdman [45] and Dai and Faeth [46] (see Figure 12 later in this section).”
Adaptive Dynamic Programming for Control: A Survey and Recent Advances (2021, methodology): “It is noted that most of the existing ADP literature is biased toward discrete-time systems [62], [63], [69], [101], [102].”