RLAIF 中 PPO 循环的实施

这部分内容有帮助吗？

参考文献

Proximal Policy Optimization Algorithms, John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, Oleg Klimov, 2017 arXiv preprint arXiv:1707.06347 (arXiv) DOI: 10.48550/arXiv.1707.06347 - 介绍PPO算法的原始论文，强化学习中策略优化的核心方法。
Training language models to follow instructions with human feedback, Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, Ryan Lowe, 2022 Advances in Neural Information Processing Systems 36 (NeurIPS), Vol. 36 DOI: 10.48550/arXiv.2203.02155 - 描述了使用人类反馈（RLHF）奖励模型通过PPO微调大型语言模型的应用，与RLAIF的PPO阶段直接相关。
High-Dimensional Continuous Control Using Generalized Advantage Estimation, John Schulman, Philipp Moritz, Sergey Levine, Michael Jordan, Pieter Abbeel, 2015 International Conference on Learning Representations (ICLR) DOI: 10.48550/arXiv.1506.02438 - 介绍了广义优势估计（GAE），一种用于降低策略梯度方法方差的技术，广泛应用于PPO。
Constitutional AI: Harmlessness from AI Feedback, Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, Carol Chen, Catherine Olsson, Christopher Olah, Danny Hernandez, Dawn Drain, Deep Ganguli, Dustin Li, Eli Tran-Johnson, Ethan Perez, Jamie Kerr, Jared Mueller, Jeffrey Ladish, Joshua Landau, Kamal Ndousse, Kamile Lukosuite, Liane Lovitt, Michael Sellitto, Nelson Elhage, Nicholas Schiefer, Noemi Mercado, Nova DasSarma, Robert Lasenby, Robin Larson, Sam Ringer, Scott Johnston, Shauna Kravec, Sheer El Showk, Stanislav Fort, Tamera Lanham, Timothy Telleen-Lawton, Tom Conerly, Tom Henighan, Tristan Hume, Samuel R. Bowman, Zac Hatfield-Dodds, Ben Mann, Dario Amodei, Nicholas Joseph, Sam McCandlish, Tom Brown, Jared Kaplan, 2022 arXiv preprint arXiv:2212.08073 DOI: 10.48550/arXiv.2212.08073 - 一篇描述使用AI反馈（RLAIF）将语言模型与原则对齐的论文，包括奖励建模和基于PPO的微调方法。