TY - GEN
T1 - Asking the Right Questions
T2 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
AU - Verma, Pulkit
AU - Marpally, Shashank Rao
AU - Srivastava, Siddharth
N1 - Funding Information:
We thank Abhyudaya Srinet for his help with the implementation. This work was supported in part by the NSF under grants IIS 1844325, IIS 1942856, and OIA 1936997.
Publisher Copyright:
© 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2021
Y1 - 2021
N2 - This paper develops a new approach for estimating an interpretable, relational model of a black-box autonomous agent that can plan and act. Our main contributions are a new paradigm for estimating such models using a rudimentary query interface with the agent and a hierarchical querying algorithm that generates an interrogation policy for estimating the agent's internal model in a user-interpretable vocabulary. Empirical evaluation of our approach shows that despite the intractable search space of possible agent models, our approach allows correct and scalable estimation of interpretable agent models for a wide class of black-box autonomous agents. Our results also show that this approach can use predicate classifiers to learn interpretable models of planning agents that represent states as images.
AB - This paper develops a new approach for estimating an interpretable, relational model of a black-box autonomous agent that can plan and act. Our main contributions are a new paradigm for estimating such models using a rudimentary query interface with the agent and a hierarchical querying algorithm that generates an interrogation policy for estimating the agent's internal model in a user-interpretable vocabulary. Empirical evaluation of our approach shows that despite the intractable search space of possible agent models, our approach allows correct and scalable estimation of interpretable agent models for a wide class of black-box autonomous agents. Our results also show that this approach can use predicate classifiers to learn interpretable models of planning agents that represent states as images.
UR - http://www.scopus.com/inward/record.url?scp=85112040687&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85112040687&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85112040687
T3 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
SP - 12024
EP - 12033
BT - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
PB - Association for the Advancement of Artificial Intelligence
Y2 - 2 February 2021 through 9 February 2021
ER -