91 citations · 226 across the 28 of their papers we have counts for
10 papers · 1 filter
The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models
Cassidy Laidlaw, Anca Dragan
Models of human behavior for prediction and collaboration tend to fall into two categories: ones that learn from large amounts of data via imitation learning, and ones that assume…
Dynamically Switching Human Prediction Models for Efficient Planning
Arjun Sripathy, Andreea Bobu, Daniel S. Brown +1
As environments involving both robots and humans become increasingly common, so does the need to account for people during planning. To plan effectively, robots must be able to res…
On complementing end-to-end human behavior predictors with planning
Liting Sun, Xiaogang Jia, Anca D. Dragan
High capacity end-to-end approaches for human motion (behavior) prediction have the ability to represent subtle nuances in human behavior, but struggle with robustness to out of di…
Choice Set Misspecification in Reward Inference
Rachel Freedman, Rohin Shah, Anca Dragan
Specifying reward functions for robots that operate in environments without a natural reward signal can be challenging, and incorrectly specified rewards can incentivise degenerate…
AvE: Assistance via Empowerment
Yuqing Du, Stas Tiomkin, Emre Kiciman +3
One difficulty in using artificial agents for human-assistive applications lies in the challenge of accurately assisting with a person's goal(s). Existing methods tend to rely on i…
Literal or Pedagogic Human? Analyzing Human Model Misspecification in Objective Learning
Smitha Milli, Anca D. Dragan
It is incredibly easy for a system designer to misspecify the objective for an autonomous system ("robot''), thus motivating the desire to have the robot learn the objective from h…