Search Results for author: Sigurdur Orn Adalgeirsson

Found 2 papers, 1 papers with code

Learning Optimal Advantage from Preferences and Mistaking it for Reward

1 code implementation3 Oct 2023 W. Bradley Knox, Stephane Hatgis-Kessell, Sigurdur Orn Adalgeirsson, Serena Booth, Anca Dragan, Peter Stone, Scott Niekum

Most recent work assumes that human preferences are generated based only upon the reward accrued within those segments, or their partial return.

B$^3$RTDP: A Belief Branch and Bound Real-Time Dynamic Programming Approach to Solving POMDPs

no code implementations22 Oct 2022 Sigurdur Orn Adalgeirsson, Cynthia Breazeal

Partially Observable Markov Decision Processes (POMDPs) offer a promising world representation for autonomous agents, as they can model both transitional and perceptual uncertainties.

Cannot find the paper you are looking for? You can Submit a new open access paper.