18 citations · 27 across the 5 of their papers we have counts for
3 papers · 1 filter
Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill Learning
Andrew Levy, Sreehari Rammohan, Alessandro Allievi +2
General purpose agents will require large repertoires of skills. Empowerment -- the maximum mutual information between skills and states -- provides a pathway for learning large co…
Models of human preference for learning reward functions
W. Bradley Knox, Stephane Hatgis-Kessell, Serena Booth +3
The utility of reinforcement learning is limited by the alignment of reward functions with the interests of human stakeholders. One promising method for alignment is to learn the r…
Reward (Mis)design for Autonomous Driving
W. Bradley Knox, Alessandro Allievi, Holger Banzhaf +2
This article considers the problem of diagnosing certain common errors in reward design. Its insights are also applicable to the design of cost functions and performance metrics mo…