I Know What You Meant: Learning Human Objectives by (Under)estimating
Their Choice Set

v1v2 (latest)

I Know What You Meant: Learning Human Objectives by (Under)estimating Their Choice Set

11 November 2020

Ananth Jonnavittula

ArXiv (abs)PDF HTML

Papers citing "I Know What You Meant: Learning Human Objectives by (Under)estimating Their Choice Set"

6 / 6 papers shown

Title
Using High-Level Patterns to Estimate How Humans Predict a Robot will Behave Sagar Parekh Lauren Bramblett Nicola Bezzo Dylan P. Losey 109 0 0 20 Sep 2024
VIEW: Visual Imitation Learning with Waypoints Ananth Jonnavittula Sagar Parekh Dylan P. Losey SSL 187 11 0 27 Apr 2024
Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning Tuan-Duong Trinh Haoyu Chen Daniel S. Brown OffRL 72 8 0 28 Nov 2022
The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types Gaurav R. Ghosal M. Zurek Daniel S. Brown Anca Dragan 109 28 0 23 Aug 2022
Physical Interaction as Communication: Learning Robot Objectives Online from Human Corrections Dylan P. Losey Andrea V. Bajcsy M. O'Malley Anca Dragan 52 36 0 06 Jul 2021
Here's What I've Learned: Asking Questions that Reveal Reward Learning Soheil Habibian Ananth Jonnavittula Dylan P. Losey 70 21 0 02 Jul 2021