%0 Conference Paper %1 conf/aistats/LiJCW24 %A Li, Zihao %A Ji, Xiang %A Chen, Minshuo %A Wang, Mengdi %B AISTATS %D 2024 %E Dasgupta, Sanjoy %E Mandt, Stephan %E Li, Yingzhen %I PMLR %K dblp %P 2737-2745 %T Policy Evaluation for Reinforcement Learning from Human Feedback: A Sample Complexity Analysis. %U http://dblp.uni-trier.de/db/conf/aistats/aistats2024.html#LiJCW24 %V 238

@inproceedings{conf/aistats/LiJCW24, added-at = {2024-05-13T00:00:00.000+0200}, author = {Li, Zihao and Ji, Xiang and Chen, Minshuo and Wang, Mengdi}, biburl = {https://www.bibsonomy.org/bibtex/2a902827efed579c441c1b138000b89c5/dblp}, booktitle = {AISTATS}, crossref = {conf/aistats/2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, ee = {https://proceedings.mlr.press/v238/li24l.html}, interhash = {2c8208a98cf71e41e0b140792ff0f9fa}, intrahash = {a902827efed579c441c1b138000b89c5}, keywords = {dblp}, pages = {2737-2745}, publisher = {PMLR}, series = {Proceedings of Machine Learning Research}, timestamp = {2024-05-20T07:23:13.000+0200}, title = {Policy Evaluation for Reinforcement Learning from Human Feedback: A Sample Complexity Analysis.}, url = {http://dblp.uni-trier.de/db/conf/aistats/aistats2024.html#LiJCW24}, volume = 238, year = 2024 }