Publication detail

Plan Reconsideration in Hybrid Agent System

ZBOŘIL, F., ZBOŘIL, F.

Original Title

Plan Reconsideration in Hybrid Agent System

English Title

Plan Reconsideration in Hybrid Agent System

Type

conference paper

Language

en

Original Abstract

bThere is discussed an idea of agent's plan reconsideration in this paper. The approach is done by a hybrid agent architecture where plan completed by a deliberative unit is checked by another reactive part. The reactive part could be of pure rective kind that means that action is selected only on basis of actual situation of the environment, or it also can be some learning predictive system (in this case Back Propagation Neural Net). Plan reconsideration depends of correlation between the established plan and actions chosen by the reflexive part on each step of the execution. Architecture of such agent is proposed in the text.

English abstract

bThere is discussed an idea of agent's plan reconsideration in this paper. The approach is done by a hybrid agent architecture where plan completed by a deliberative unit is checked by another reactive part. The reactive part could be of pure rective kind that means that action is selected only on basis of actual situation of the environment, or it also can be some learning predictive system (in this case Back Propagation Neural Net). Plan reconsideration depends of correlation between the established plan and actions chosen by the reflexive part on each step of the execution. Architecture of such agent is proposed in the text.

Keywords

Agent System, Planning, Neural Network

RIV year

2003

Released

08.09.2003

Location

Ostrava

ISBN

80-85988-88-7

Book

Proceedings of XXVth International Autumn Colloquium ASIS 2003

Pages from

315

Pages to

321

Pages count

7

Documents

BibTex


@inproceedings{BUT14201,
  author="František {Zbořil} and František {Zbořil}",
  title="Plan Reconsideration in Hybrid Agent System",
  annote="bThere is discussed an idea of agent's plan reconsideration in this
paper. The approach is done by a hybrid agent architecture where plan
completed by a deliberative unit is checked by another reactive part.
The reactive part could be of pure rective kind that means that action
is selected only on basis of actual situation of the environment, or it
also can be some learning predictive system (in this case Back
Propagation Neural Net). Plan reconsideration depends of correlation
between the established plan and actions chosen by the reflexive part
on each step of the execution. Architecture of such agent is proposed
in the text.",
  booktitle="Proceedings of XXVth International Autumn Colloquium ASIS 2003",
  chapter="14201",
  year="2003",
  month="september",
  pages="315--321",
  type="conference paper"
}