Finding safe policies in model-based active learning

Open Access

Abstract

Trabajo presentado al IROS: "Machine Learning in Planning and Control of Robot Motion Workshop" (IROS MLPC), celebrado en Chicago, Illinois (US) del 14 al 18 de septiembre. ; Este ítem (excepto textos e imágenes no creados por el autor) está sujeto a una licencia de Creative Commons: Attribution-NonCommercial-NoDerivs 3.0 Spain. ; Task learning in robotics is a time-consuming process, and model-based reinforcement learning algorithms have been proposed to learn with just a small amount of experiences. However, reducing the number of experiences used to learn implies that the algorithm may overlook crucial actions required to get an optimal behavior. For example, a robot may learn simple policies that have a high risk of not reaching the goal because they often fall into dead-ends. We propose a new method that allows the robot to reason about dead-ends and their causes. Analyzing its current model and experiences, the robot will hypothesize the possible causes for the dead-end, and identify the actions that may cause it, marking them as dangerous. Afterwards, whenever a dangerous action is included into a plan which has a high risk of leading to a dead-end, the special action request teacher confirmation will be triggered by the robot to actively confirm with a teacher that the planned risky action should be executed. This method permits learning safer policies with the addition of just a few teacher demonstration requests. Experimental validation of the approach is provided in two different scenarios: a robotic assembly task and a domain from the international planning competition. Our approach gets success ratios very close to 1 in problems where previous approaches had high probabilities of reaching dead-ends. ; This work was supported by EU Project IntellAct FP7-ICT2009-6-269959, by CSIC project MANIPlus 201350E102 and by the Spanish Ministry of Science and Innovation under project PAU+ DPI2011-27510. D. Martínez is also supported by the Spanish Ministry of Education, Culture and Sport via a FPU doctoral grant (FPU12-04173). ; Peer Reviewed