Model-free Q-learning designs for discrete-time zero-sum games with application to H-infinity control
By Asma Al-Tamimi, Frank L. Lewis, Murad Abu-Khalaf. European Control Conference, 2007
554 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computational Theory and Mathematics, Electrical and Electronic Engineering
View Paper: https://www.semanticscholar.org/paper/2d3d295a0c70931bd5ce6ed0e62a6c5e6f2acf63
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
- Derong Liu
- Qinglai Wei
- Frank L. Lewis
- Huaguang Zhang
- Zhong-Ping Jiang
- Draguna L. Vrabie
- Yu Jiang
- Ding Wang
In Computational Theory and Mathematics
- Derong Liu
- Frank L. Lewis
- Qinglai Wei
- Zhong-Ping Jiang
- Ding Wang
- Hamidreza Modares
- Huaguang Zhang
- Draguna L. Vrabie
In Electrical and Electronic Engineering
- Frank L. Lewis
- Derong Liu
- Zhong-Ping Jiang
- Qinglai Wei
- Hamidreza Modares
- Yu Jiang
- Huaguang Zhang
- Draguna L. Vrabie
Citations in the corpus
- Discrete-Time Nonlinear HJB Solution Using Approximate Dynamic Programming: Convergence Proof (2008, methodology): “In our previous work [3], [4], we studied ADP value iteration techniques to solve the zero-sum”
- An iterative adaptive dynamic programming method for solving a class of nonlinear zero-sum differential games (2011, result): “Similar works can also be seen in Al-Tamimi et al. (2007) andWei, Zhang, and Dai (2009).”
- Adaptive optimal control for continuous-time linear systems based on policy iteration (2009, unknown): “In the recent works Al-Tamimi, Abu-Khalaf, and Lewis (2007) and Landelius (1997) there have been introduced policy iteration algorithms which converge to the discrete time H 2 and H-infinity optimal state feedback control solution without the requirement of a stabilizing controller at each…”
- Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics (2012, methodology): “ẋ = Ax+Bu (1) where x∈Rn is the system state fully available for feedback control design; u ∈ Rm is the control input; A ∈ Rn×n and B ∈ Rn×m are unknown constant matrices.”
- Reinforcement learning and adaptive dynamic programming for feedback control (2009, methodology): “It is important to note that, given any admissible policy, its value may be determined by evaluating the infinite sum (3).”
- Adaptive Dynamic Programming: An Introduction (2009, background): “In addition, practical applications of ADP with significant economic impact are of great demand.”
- Adaptive Dynamic Programming and Adaptive Optimal Output Regulation of Linear Systems (2016, background): “Examples of such noise are random noise [3] and sinusoidal signal [19].”