Publication

Learning rules from cause-effects explanations

Technical Report (2008)

IRI code

IRI-TR-08-04

File

Download the digital copy of the doc pdf document

Abstract

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.

Categories

intelligent robots, learning (artificial intelligence).

Author keywords

robot-human interaction, cause-effect learning, rule based learning

Scientific reference

A. Agostini, E. Celaya, C. Torras and F. Wörgötter. Learning rules from cause-effects explanations. Technical Report IRI-TR-08-04, Institut de Robòtica i Informàtica Industrial, CSIC-UPC, 2008.