387 citations · 971 across the 40 of their papers we have counts for
8 papers · 1 filter
Human-AI Learning Performance in Multi-Armed Bandits
Ravi Pandya, Sandy H. Huang, Dylan Hadfield-Menell +1
People frequently face challenging decision-making problems in which outcomes are uncertain or unknown. Artificial intelligence (AI) algorithms exist that can outperform humans at…
On the Geometry of Adversarial Examples
Marc Khoury, Dylan Hadfield-Menell
Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statist…
Legible Normativity for AI Alignment: The Value of Silly Rules
Dylan Hadfield-Menell, McKane Andrus, Gillian K. Hadfield
It has become commonplace to assert that autonomous agents will have to be built to follow human rules of behavior--social norms and laws. But human laws and norms are complex and…
Active Inverse Reward Design
Sören Mindermann, Rohin Shah, Adam Gleave +1
Designers of AI agents often iterate on the reward function in a trial-and-error process until they get the desired behavior, but this only guarantees good behavior in the training…
An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning
Dhruv Malik, Malayandi Palaniappan, Jaime F. Fisac +3
Our goal is for AI systems to correctly identify and act according to their human user's objectives. Cooperative Inverse Reinforcement Learning (CIRL) formalizes this value alignme…
Simplifying Reward Design through Divide-and-Conquer
Ellis Ratner, Dylan Hadfield-Menell, Anca D. Dragan
Designing a good reward function is essential to robot planning and reinforcement learning, but it can also be challenging and frustrating. The reward needs to work across multiple…
Incomplete Contracting and AI Alignment
Dylan Hadfield-Menell, Gillian Hadfield
We suggest that the analysis of incomplete contracting developed by law and economics researchers can provide a useful framework for understanding the AI alignment problem and help…
Expressive Robot Motion Timing
Allan Zhou, Dylan Hadfield-Menell, Anusha Nagabandi +1
Our goal is to enable robots to \emph{time} their motion in a way that is purposefully expressive of their internal states, making them more transparent to people. We start by inve…