no code implementations • 14 Dec 2023 • Akash Ratheesh, Ofer Dagan, Nisar R. Ahmed, Jay McMahon
This paper considers the problem of evaluating an autonomous system's competency in performing a task, particularly when working in dynamic and uncertain environments.
no code implementations • 20 Jul 2023 • Christopher Funk, Ofer Dagan, Benjamin Noack, Nisar R. Ahmed
We then test our new non-monolithic CI algorithm on a large-scale target tracking simulation and show that it achieves a tighter bound and a more accurate estimate compared to the original monolithic CI.
no code implementations • 17 Feb 2023 • Aastha Acharya, Rebecca Russell, Nisar R. Ahmed
Giving autonomous agents the ability to forecast their own outcomes and uncertainty will allow them to communicate their competencies and be used more safely.
no code implementations • 21 Jun 2022 • Aastha Acharya, Rebecca Russell, Nisar R. Ahmed
For safe and reliable deployment in the real world, autonomous agents must elicit appropriate levels of trust from human users.
no code implementations • 23 Mar 2022 • Aastha Acharya, Rebecca Russell, Nisar R. Ahmed
For autonomous agents to act as trustworthy partners to human users, they must be able to reliably communicate their competency for the tasks they are asked to perform.
no code implementations • 17 Nov 2020 • Aastha Acharya, Rebecca Russell, Nisar R. Ahmed
The deployment of reinforcement learning (RL) in the real world comes with challenges in calibrating user trust and expectations.
no code implementations • 2 Apr 2020 • Michael L. Iuzzolino, Tetsumichi Umada, Nisar R. Ahmed, Danielle A. Szafir
A current standard policy for AL is to query the oracle (e. g., the analyst) to refine labels for datapoints where the classifier has the highest uncertainty.
1 code implementation • 15 Oct 2018 • Brett W. Israelsen, Nisar R. Ahmed, Eric Frew, Dale Lawrence, Brian Argrow
Markov decision processes underlie much of the theory of reinforcement learning, and are commonly used for planning and decision making under uncertainty in robotics and autonomous systems.
no code implementations • 8 Nov 2017 • Brett W. Israelsen, Nisar R. Ahmed
People who design, use, and are affected by autonomous artificially intelligent agents want to be able to \emph{trust} such agents -- that is, to know that these agents will perform correctly, to understand the reasoning behind their actions, and to know how to use them appropriately.