Erdem Bıyık

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Stephen Casper, Xander Davies, Claudia Shi et al. · arXiv (Cornell University) · 2023 · 88 citations · Full text

Artificial Intelligence, Engineering, Game Theory +23

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

Erdem Bıyık, Malayandi Palan, Nicholas C. Landolfi et al. · arXiv (Cornell University) · 2019 · 54 citations · Full text

Artificial Intelligence, Right Reward Function, Engineering +24

Active Learning of Reward Dynamics from Hierarchical Queries

Chandrayee Basu, Erdem Bıyık, Zhixun He et al. · 2019 · 28 citations

Artificial Intelligence, Engineering, Machine Learning +17

Batch Active Learning Using Determinantal Point Processes

Erdem Bıyık, Kenneth Wang, Nima Anari et al. · arXiv (Cornell University) · 2019 · 22 citations · Full text

Multiple Instance Learning, Machine Vision, Machine Learning +15

Learning reward functions from diverse sources of human feedback: Optimally integrating demonstrations and preferences

Erdem Bıyık, Dylan P. Losey, Malayandi Palan et al. · The International Journal of Robotics Research · 2021 · 21 citations · Full text

Artificial Intelligence, Reward Function, Engineering +21