In this work we propose a learning system to learn on-line an action policy coded in rules using natural human instructions about cause-effect relations in currently observed situations. The instructions only on currently observed situations avoid complicated descriptions of long-run action sequences and complete world dynamics. Human interaction is only required if the system fails to obtain the expected results when applying a rule, or fails to resolve the task with the knowledge acquired so far.
CitationAgostini, Alejandro; Celaya, Enric; Torras, Carme; Wörgötter, Florentin. " Learning rules from cause-effects explanations". Technical Report IRI-DT-08-04, Institut de Robòtica i Informàtica Industrial, CSIC-UPC, 2008.
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder. If you wish to make any use of the work not provided for in the law, please contact: firstname.lastname@example.org