Fighting Failures with FIRE: Failure Identification to Reduce Expert Burden in Intervention-Based Learning.

作者: Filip Maric , Jonathan Kelly , Trevor Ablett

DOI:

关键词:

摘要: Supervised imitation learning, also known as behavioral cloning, suffers from distribution drift leading to failures during policy execution. One approach to mitigate this issue is to …

参考文章(34)
John Schulman, None, Trust Region Policy Optimization international conference on machine learning. pp. 1889- 1897 ,(2015)
Stephane Ross, Narek Melik-Barkhudarov, Kumar Shaurya Shankar, Andreas Wendel, Debadeepta Dey, J. Andrew Bagnell, Martial Hebert, Learning monocular reactive UAV control in cluttered natural environments international conference on robotics and automation. pp. 1765- 1772 ,(2013) , 10.1109/ICRA.2013.6630809
, Generative Adversarial Nets neural information processing systems. ,vol. 27, pp. 2672- 2680 ,(2014) , 10.3156/JSOFT.29.5_177_2
Dean A. Pomerleau, ALVINN: An Autonomous Land Vehicle in a Neural Network neural information processing systems. ,vol. 1, pp. 305- 313 ,(1988) , 10.1184/R1/6603146.V1
Beomjoon Kim, Joelle Pineau, Maximum Mean Discrepancy Imitation Learning. robotics: science and systems. ,vol. 09, ,(2013) , 10.15607/RSS.2013.IX.038
Alessandro Giusti, Jérôme Guzzi, Dan C Cireşan, Fang-Lin He, Juan P Rodríguez, Flavio Fontana, Matthias Faessler, Christian Forster, Jürgen Schmidhuber, Gianni Di Caro, Davide Scaramuzza, Luca M Gambardella, None, A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots international conference on robotics and automation. ,vol. 1, pp. 661- 667 ,(2016) , 10.1109/LRA.2015.2509024
Beat Flepp, Lawrence D. Jackel, Davide Del Testa, Karol Zieba, Urs Muller, Mathew Monfort, Mariusz Bojarski, Prasoon Goyal, Xin Zhang, Daniel Dworakowski, Bernhard Firner, Jiakai Zhang, Jake Zhao, End to End Learning for Self-Driving Cars arXiv: Computer Vision and Pattern Recognition. ,(2016)
Kyunghyun Cho, Jiakai Zhang, Query-Efficient Imitation Learning for End-to-End Autonomous Driving arXiv: Learning. ,(2016)
Michael Laskey, Sam Staszak, Wesley Yu-Shu Hsieh, Jeffrey Mahler, Florian T. Pokorny, Anca D. Dragan, Ken Goldberg, SHIV: Reducing supervisor burden in DAgger using support vectors for efficient learning from demonstrations in high dimensional state spaces international conference on robotics and automation. pp. 462- 469 ,(2016) , 10.1109/ICRA.2016.7487167
J. Andrew Bagnell, Byron Boots, Geoffrey J. Gordon, Arun Venkatraman, Wen Sun, Deeply AggreVaTeD: differentiable imitation learning for sequential prediction international conference on machine learning. pp. 3309- 3318 ,(2017)