Using options to improve robustness of imitation learning against adversarial attacks

Prithviraj Dasgupta

doi:10.1117/12.2585849

12 April 2021 Using options to improve robustness of imitation learning against adversarial attacks

Prithviraj Dasgupta

Proceedings Volume 11746, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III; 1174610 (2021) https://doi.org/10.1117/12.2585849
Event: SPIE Defense + Commercial Sensing, 2021, Online Only

Abstract

Imitation learning has been shown to be a successful learning technique in scenarios where autonomous agents have to adapt their operation across diverse environments or domains. The main principle underlying imitation learning is to determine a state-to-action mapping, called a policy, from trajectories demonstrated by an expert. We consider the problem of imitation learning under adversarial settings where the expert could be malicious and intermittently give incorrect demonstrations to misguide the learning agent. We propose a technique using temporally extended policies called options to make a learning agent robust against adversarial expert demonstrations. Experimental evaluation of our proposed technique for a game playing AI shows that a learning agent using our options based technique can successfully resist deterioration in its task performance as compared to using conventional reinforcement learning, when an expert adversarially modifies the demonstrations either randomly or strategically.

Conference Presentation

Citation Download Citation

Prithviraj Dasgupta "Using options to improve robustness of imitation learning against adversarial attacks", Proc. SPIE 11746, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III, 1174610 (12 April 2021); https://doi.org/10.1117/12.2585849

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available