### 抄録

In this paper, a new adaptive actor-critic algorithm is proposed under the assumption that a predictive model (such as kinematic model for a robot) is available and only the measurement at time k is used to update the learning algorithms. Two value-functions are realized as a pure static mapping, according to the fact that they can be reduced to nonlinear current estimators, which can be easily constructed by using any artificial neural networks (NNs) with sigmoidal function or radial basis function (RBF), if all the inputs to the present value-functions are based on simulated experiences generated from the predictive model. In addition, if a predictive model is assumed to be used to construct a model-based actor (MBA) in the framework of adaptive actor-critic approach, then this type of MBA can be viewed as a network whose connection weights are composed of the elements of feedback gain matrix, so that the temporal difference (TD) learning can also be naturally applied to update the weights of the actor. Since the present method can update the learning by using only one measurement at time k, a relatively fast learning is expected, compared with the previous approach that needs two measurements at times k and k + 1 to update the actor-critic networks. The effectiveness of the proposed approach is illustrated by simulating a trajectory-tracking control problem for a nonholonomic mobile robot.

元の言語 | 英語 |
---|---|

ページ（範囲） | 3960-3965 |

ページ数 | 6 |

ジャーナル | Unknown Journal |

巻 | 4 |

出版物ステータス | 出版済み - 2002 |

外部発表 | Yes |

### Fingerprint

### All Science Journal Classification (ASJC) codes

- Software
- Control and Systems Engineering

### これを引用

*Unknown Journal*,

*4*, 3960-3965.

**Control of nonholonomic mobile robot by an adaptive actor-critic method with simulated experience based value-functions.** / Syam, Rafiuddin; Watanabe, Keigo; Izumi, Kiyotaka; Kiguchi, Kazuo.

研究成果: ジャーナルへの寄稿 › 記事

*Unknown Journal*, 巻. 4, pp. 3960-3965.

}

TY - JOUR

T1 - Control of nonholonomic mobile robot by an adaptive actor-critic method with simulated experience based value-functions

AU - Syam, Rafiuddin

AU - Watanabe, Keigo

AU - Izumi, Kiyotaka

AU - Kiguchi, Kazuo

PY - 2002

Y1 - 2002

N2 - In this paper, a new adaptive actor-critic algorithm is proposed under the assumption that a predictive model (such as kinematic model for a robot) is available and only the measurement at time k is used to update the learning algorithms. Two value-functions are realized as a pure static mapping, according to the fact that they can be reduced to nonlinear current estimators, which can be easily constructed by using any artificial neural networks (NNs) with sigmoidal function or radial basis function (RBF), if all the inputs to the present value-functions are based on simulated experiences generated from the predictive model. In addition, if a predictive model is assumed to be used to construct a model-based actor (MBA) in the framework of adaptive actor-critic approach, then this type of MBA can be viewed as a network whose connection weights are composed of the elements of feedback gain matrix, so that the temporal difference (TD) learning can also be naturally applied to update the weights of the actor. Since the present method can update the learning by using only one measurement at time k, a relatively fast learning is expected, compared with the previous approach that needs two measurements at times k and k + 1 to update the actor-critic networks. The effectiveness of the proposed approach is illustrated by simulating a trajectory-tracking control problem for a nonholonomic mobile robot.

AB - In this paper, a new adaptive actor-critic algorithm is proposed under the assumption that a predictive model (such as kinematic model for a robot) is available and only the measurement at time k is used to update the learning algorithms. Two value-functions are realized as a pure static mapping, according to the fact that they can be reduced to nonlinear current estimators, which can be easily constructed by using any artificial neural networks (NNs) with sigmoidal function or radial basis function (RBF), if all the inputs to the present value-functions are based on simulated experiences generated from the predictive model. In addition, if a predictive model is assumed to be used to construct a model-based actor (MBA) in the framework of adaptive actor-critic approach, then this type of MBA can be viewed as a network whose connection weights are composed of the elements of feedback gain matrix, so that the temporal difference (TD) learning can also be naturally applied to update the weights of the actor. Since the present method can update the learning by using only one measurement at time k, a relatively fast learning is expected, compared with the previous approach that needs two measurements at times k and k + 1 to update the actor-critic networks. The effectiveness of the proposed approach is illustrated by simulating a trajectory-tracking control problem for a nonholonomic mobile robot.

UR - http://www.scopus.com/inward/record.url?scp=0036057068&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036057068&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0036057068

VL - 4

SP - 3960

EP - 3965

JO - Quaternary International

JF - Quaternary International

SN - 1040-6182

ER -