Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

• DOI: 10.3929/ethz-b-000651806
• Publication Date: 2023-01-01
• Authors: Casper, Stephen; Davies, Xander; Shi, Claudia; Krendl Gilbert, T...; Scheurer, Jérémy; Rando Ramirez, Ja...; Freedman, Rachel; Korbak, Tomasz; Lindner, David; i...; Freire, Pedro; Wang, Tony; Marks, Samuel; Segerie, Charbel-...; Carroll, Micah; Peng, Andi; Christoffersen, P...; Damani, Mehul; Slocum, Stewart; Anwar, Usman; Siththaranjan, Anand; Nadeau, Max; Michaud, Eric J.; Pfau, Jacob; Krasheninnikov, D...; Chen, Xin; Langosco, Lauro; Hase, Peter; Bıyık, Erdem; Dragan, Anca; Krueger, David; Sadigh, Dorsa; Hadfield-Menell, ...
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Computer Science - Computation and Language; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; Computation and Language (cs.CL); Machine Learning (cs.LG)

ISSN:2835-8856<br/>Transactions on Machine Learning Research<br/>