Finding safe policies in model-based active learning
Estadístiques de LA Referencia / Recolecta
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/27799
Tipus de documentText en actes de congrés
Data publicació2014
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-SenseObraDerivada 3.0 Espanya
ProjecteINTELLACT - Intelligent observation and execution of Actions and manipulations (EC-FP7-269959)
Abstract
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
CitacióMartínez, D.; Alenyà, G.; Torras, C. Finding safe policies in model-based active learning. A: IROS Machine Learning in Planning and Control of Robot Motion Workshop. "Proceedings of the 2014 IROS Machine Learning in Planning and Control of Robot Motion Worksho". Chicago: 2014, p. 1-6.
Versió de l'editorhttp://www.cs.unm.edu/amprg/mlpc14Workshop/proceedings.html
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
1560-Finding-Sa ... -Based-Active-Learning.pdf | 1,669Mb | Visualitza/Obre |