Gaurav R. Ghosal — accepted AI-conference papers

2024

A Generalized Acquisition Function for Preference-based Reward Learning

Evan Ellis, Gaurav R. Ghosal, Stuart J. Russell, Anca Dragan, Erdem Bıyık

ICRA 2024poster

Preference-based reward learning is a popular technique for teaching robots and autonomous systems how a human user wants them to perform a task. Previous works have shown that actively synthesizing preference queries to maximize information gain about the reward function parameters improves data ef…

Cited by 3 Source ↗Scholar ↗

2023

The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types

Gaurav R. Ghosal, Matthew Zurek, Daniel S. Brown, Anca D. Dragan

AAAI 2023technical

When inferring reward functions from human behavior (be it demonstrations, comparisons, physical corrections, or e-stops), it has proven useful to model the human as making noisy-rational choices, with a "rationality coefficient" capturing how much noise or entropy we expect to see in the human beha…

Cited by 37 Source ↗PDF ↗Scholar ↗