Evan Ellis
Papers
1
Total Citations
6
H-Index
1
About
Evan Ellis is a rising researcher at the intersection of robotics, machine learning, and human-robot interaction, with a primary focus on preference-based reward learning. His most cited work, "A Generalized Acquisition Function for Preference-based Reward Learning" (2024, 6 citations), introduces a novel framework for actively synthesizing preference queries that maximize information gain about reward function parameters. This contribution addresses a critical bottleneck in teaching autonomous systems how humans want them to perform tasks, enabling more efficient and intuitive robot learning from human feedback. By generalizing acquisition functions beyond traditional approaches, Ellis's research helps robots ask better questions, reducing the data burden on human teachers while improving alignment with user intent. Though early in his career, his work is already shaping how researchers think about active learning for reward modeling, with implications for assistive robotics, autonomous driving, and collaborative AI systems. Ellis's contributions are particularly notable for bridging theoretical rigor with practical deployment considerations, making him a promising voice in the growing field of human-aligned artificial intelligence.
Research Focus
Key Achievements
Top Papers
- 1A Generalized Acquisition Function for Preference-based Reward Learning6 citations · 2024