### Abstract

This paper studies the adaptive and optimal output feedback control problem using approximate dynamic programming. It is shown that, under the recursive algorithm, the control policy converges to its optimal value, up to a constant proportional to the magnitude of the inaccuracy caused by observation errors. On the basis of this result, direct adaptive output feedback strategies are developed for solving both discrete-time and continuous-time LQR problems with uncertain parameters. Finally, numerical examples are given to demonstrate the efficiency of the proposed control schemes.

Original language | English (US) |
---|---|

Title of host publication | Proceedings of the 29th Chinese Control Conference, CCC'10 |

Pages | 5815-5820 |

Number of pages | 6 |

State | Published - 2010 |

Event | 29th Chinese Control Conference, CCC'10 - Beijing, China Duration: Jul 29 2010 → Jul 31 2010 |

### Other

Other | 29th Chinese Control Conference, CCC'10 |
---|---|

Country | China |

City | Beijing |

Period | 7/29/10 → 7/31/10 |

### Fingerprint

### Keywords

- Adaptive control
- ADP
- Policy iteration
- Reinforcement learning

### ASJC Scopus subject areas

- Control and Systems Engineering

### Cite this

*Proceedings of the 29th Chinese Control Conference, CCC'10*(pp. 5815-5820). [5573203]

**Approximate dynamic programming for output feedback control.** / Jiang, Yu; Jiang, Zhong-Ping.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*Proceedings of the 29th Chinese Control Conference, CCC'10.*, 5573203, pp. 5815-5820, 29th Chinese Control Conference, CCC'10, Beijing, China, 7/29/10.

}

TY - GEN

T1 - Approximate dynamic programming for output feedback control

AU - Jiang, Yu

AU - Jiang, Zhong-Ping

PY - 2010

Y1 - 2010

N2 - This paper studies the adaptive and optimal output feedback control problem using approximate dynamic programming. It is shown that, under the recursive algorithm, the control policy converges to its optimal value, up to a constant proportional to the magnitude of the inaccuracy caused by observation errors. On the basis of this result, direct adaptive output feedback strategies are developed for solving both discrete-time and continuous-time LQR problems with uncertain parameters. Finally, numerical examples are given to demonstrate the efficiency of the proposed control schemes.

AB - This paper studies the adaptive and optimal output feedback control problem using approximate dynamic programming. It is shown that, under the recursive algorithm, the control policy converges to its optimal value, up to a constant proportional to the magnitude of the inaccuracy caused by observation errors. On the basis of this result, direct adaptive output feedback strategies are developed for solving both discrete-time and continuous-time LQR problems with uncertain parameters. Finally, numerical examples are given to demonstrate the efficiency of the proposed control schemes.

KW - Adaptive control

KW - ADP

KW - Policy iteration

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=78650246160&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650246160&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9787894631046

SP - 5815

EP - 5820

BT - Proceedings of the 29th Chinese Control Conference, CCC'10

ER -