activity
20182022
most citedAsking Easy Questions: A User-Friendly Approach to Active Reward Learning

54 citations · 56 across the 4 of their papers we have counts for

collaborators

6 papers

cs.LG20221 cited

Unsupervised language models for disease variant prediction

Allan Zhou, Nicholas C. Landolfi, Daniel C. O'Neill

There is considerable interest in predicting the pathogenicity of protein variants in human genes. Due to the sparsity of high quality labels, recent approaches turn to \textit{uns…

stat.ME2022

Probabilistic Modeling Using Tree Linear Cascades

Nicholas C. Landolfi, Sanjay Lall

We introduce tree linear cascades, a class of linear structural equation models for which the error variables are uncorrelated but need not be Gaussian nor independent. We show tha…

cs.RO201954 cited

Asking Easy Questions: A User-Friendly Approach to Active Reward Learning

Erdem Bıyık, Malayandi Palan, Nicholas C. Landolfi +2

Robots can learn the right reward function by querying a human expert. Existing approaches attempt to choose questions where the robot is most uncertain about the human's response;…

cs.LG2019

A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning

Nicholas C. Landolfi, Garrett Thomas, Tengyu Ma

The aim of multi-task reinforcement learning is two-fold: (1) efficiently learn by training against multiple tasks and (2) quickly adapt, using limited samples, to a variety of new…

cs.RO20191 cited

Learning Reward Functions by Integrating Human Demonstrations and Preferences

Malayandi Palan, Nicholas C. Landolfi, Gleb Shevchuk +1

Our goal is to accurately and efficiently learn reward functions for autonomous robots. Current approaches to this problem include inverse reinforcement learning (IRL), which uses…

cs.RO2018

Social Cohesion in Autonomous Driving

Nicholas C. Landolfi, Anca D. Dragan

Autonomous cars can perform poorly for many reasons. They may have perception issues, incorrect dynamics models, be unaware of obscure rules of human traffic systems, or follow cer…