Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback. Casper, S., Davies, X., Shi, C., Gilbert, T. K., Scheurer, J., Rando, J., Freedman, R., Korbak, T., Lindner, D., Freire, P., Wang, T. T., Marks, S., Ségerie, C., Carroll, M., Peng, A., Christoffersen, P. J. K., Damani, M., Slocum, S., Anwar, U., Siththaranjan, A., Nadeau, M., Michaud, E. J., Pfau, J., Krasheninnikov, D., Chen, X., Langosco, L., Hase, P., Biyik, E., Dragan, A. D., Krueger, D., Sadigh, D., & Hadfield-Menell, D. Trans. Mach. Learn. Res., 2023.
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback. [link]Link  Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback. [link]Paper  bibtex   
@article{journals/tmlr/CasperDSGSRFKLF23,
  added-at = {2024-08-02T00:00:00.000+0200},
  author = {Casper, Stephen and Davies, Xander and Shi, Claudia and Gilbert, Thomas Krendl and Scheurer, Jérémy and Rando, Javier and Freedman, Rachel and Korbak, Tomasz and Lindner, David and Freire, Pedro and Wang, Tony Tong and Marks, Samuel and Ségerie, Charbel-Raphaël and Carroll, Micah and Peng, Andi and Christoffersen, Phillip J. K. and Damani, Mehul and Slocum, Stewart and Anwar, Usman and Siththaranjan, Anand and Nadeau, Max and Michaud, Eric J. and Pfau, Jacob and Krasheninnikov, Dmitrii and Chen, Xin and Langosco, Lauro and Hase, Peter and Biyik, Erdem and Dragan, Anca D. and Krueger, David and Sadigh, Dorsa and Hadfield-Menell, Dylan},
  biburl = {https://www.bibsonomy.org/bibtex/234f66ba045a32cc110d9fb932d5e1b6c/dblp},
  ee = {https://openreview.net/forum?id=bx24KpJ4Eb},
  interhash = {cd3e20701f0845328d62b36b1d2a89b4},
  intrahash = {34f66ba045a32cc110d9fb932d5e1b6c},
  journal = {Trans. Mach. Learn. Res.},
  keywords = {dblp},
  timestamp = {2024-08-05T07:13:15.000+0200},
  title = {Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.},
  url = {http://dblp.uni-trier.de/db/journals/tmlr/tmlr2023.html#CasperDSGSRFKLF23},
  volume = 2023,
  year = 2023
}

Downloads: 0