Fetching the paper…
Reading the bibliography…
We point out a few pitfalls in implementing gradient estimation for KL divergence in RL training for LLM, as seen in a number of open source projects and papers.
Pytorch: An imperative style, high-performance deep learning library. arxiv 2019
Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al · 1912
Earlier work this paper cites.
Simple statistical gradient-following algorithms for connectionist reinforcement learning
Ronald J Williams · 1992
Earlier work this paper cites.
Reinforcement Learning: An Introduction
R. Sutton and A. Barto · 1998
Earlier work this paper cites.
Monte Carlo statistical methods , volume 2
Christian P Robert, George Casella, and George Casella · 1999
Earlier work this paper cites.
Policy gradient methods for reinforcement learning with function approximation
Richard S Sutton, David McAllester, Satinder Singh, and Yishay Mansour · 1999
Earlier work this paper cites.
Monte carlo methods in financial engineering, 2004
P Glasserman · 2004
Earlier work this paper cites.
Maximum entropy inverse reinforcement learning
Brian D Ziebart, Andrew L Maas, J Andrew Bagnell, Anind K Dey, et al · 2008
Earlier work this paper cites.
Auto-encoding variational bayes, 2013
Diederik P Kingma, Max Welling, et al · 2013
Earlier work this paper cites.
Black box variational inference
Rajesh Ranganath, Sean Gerrish, and David Blei · 2014
Earlier work this paper cites.
Stochastic backpropagation and approximate inference in deep generative models
Danilo Jimenez Rezende, Shakir Mohamed, and Daan Wierstra · 2014
Earlier work this paper cites.
Variational inference for monte carlo objectives
Andriy Mnih and Danilo Rezende · 2016
Earlier work this paper cites.
Deep reinforcement learning from human preferences
Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei · 2017
Earlier work this paper cites.
kl-approx blogpost
John Schulman · 2017
Earlier work this paper cites.
JAX: composable transformations of Python+NumPy programs, 2018
James Bradbury, Roy Frostig, Peter Hawkins, Matthew James Johnson, Chris Leary, Dougal Maclaurin, George Necula, Adam Paszke, Jake VanderPlas, Skye Wanderman-Milne, and Qiao Zhang · 2018
Cited alongside, same era.
Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor
Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine · 2018
Cited alongside, same era.
Buy 4 reinforce samples, get a baseline for free!
Wouter Kool, Herke van Hoof, and Max Welling · 2019
Cited alongside, same era.
Fine-tuning language models from human preferences
Daniel M Ziegler, Nisan Stiennon, Jeffrey Wu, Tom B Brown, Alec Radford, Dario Amodei, Paul Christiano, and Geoffrey Irving · 2019
Cited alongside, same era.
Monte-carlo tree search as regularized policy optimization
Jean-Bastien Grill, Florent Altché, Yunhao Tang, Thomas Hubert, Michal Valko, Ioannis Antonoglou, and Rémi Munos · 2020
Cited alongside, same era.
Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, et al · 2024
Later among the works it cites.
Audrey Huang, Wenhao Zhan, Tengyang Xie, Jason D Lee, Wen Sun, Akshay Krishnamurthy, and Dylan J Foster · 2024
Later among the works it cites.
Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, et al · 2024
Later among the works it cites.
Tülu 3: Pushing frontiers in open language model post-training
Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V. Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D. Hwang, Jiangjiang Yang, Ronan Le Bras, Oyvind Tafjord, Chris Wilhelm, Luca Soldaini, Noah A. Smith, Yizhong Wang, Pradeep Dasigi, and Hannaneh Hajishirzi · 2024
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Trl: Transformer reinforcement learning
Leandro von Werra, Younes Belkada, Lewis Tunstall, Edward Beeching, Tristan Thrush, Nathan Lambert, Shengyi Huang, Kashif Rasul, and Quentin Gallouédec · 2020
Cited alongside, same era.
Measuring mathematical problem solving with the math dataset
Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt · 2021
Cited alongside, same era.
Training language models to follow instructions with human feedback
Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al · 2022
Cited alongside, same era.
Scaling laws for reward model overoptimization
Leo Gao, John Schulman, and Jacob Hilton · 2023
Cited alongside, same era.
On-policy distillation of language models: Learning from self-generated mistakes, 2024
Rishabh Agarwal, Nino Vieillard, Yongchao Zhou, Piotr Stanczyk, Sabela Ramos, Matthieu Geist, and Olivier Bachem · 2024
Cited alongside, same era.
A general theoretical paradigm to understand learning from human preferences
Mohammad Gheshlaghi Azar, Zhaohan Daniel Guo, Bilal Piot, Remi Munos, Mark Rowland, Michal Valko, and Daniele Calandriello · 2024
Cited alongside, same era.
Contrastive policy gradient: Aligning llms on sequence-level scores in a supervised-friendly fashion
Yannis Flet-Berliac, Nathan Grinsztajn, Florian Strub, Bill Wu, Eugene Choi, Chris Cremer, Arash Ahmadian, Yash Chandak, Mohammad Gheshlaghi Azar, Olivier Pietquin, et al · 2024
Cited alongside, same era.
Deepseekmath: Pushing the limits of mathematical reasoning in open language models
Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, et al · 2024
Later among the works it cites.
Generalized preference optimization: A unified approach to offline alignment
Yunhao Tang, Zhaohan Daniel Guo, Zeyu Zheng, Daniele Calandriello, Rémi Munos, Mark Rowland, Pierre Harvey Richemond, Michal Valko, Bernardo Ávila Pires, and Bilal Piot · 2024
Later among the works it cites.
Soft policy optimization: Online off-policy rl for sequence models
Taco Cohen, David W Zhang, Kunhao Zheng, Yunhao Tang, Remi Munos, and Gabriel Synnaeve · 2025
Closest in time.
Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning
Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al · 2025
Closest in time.
Understanding r1-zero-like training: A critical perspective
Zichen Liu, Changyu Chen, Wenjun Li, Penghui Qi, Tianyu Pang, Chao Du, Wee Sun Lee, and Min Lin · 2025
Closest in time.
Rl-finetuning llms from on-and off-policy data with a single algorithm
Yunhao Tang, Taco Cohen, David W Zhang, Michal Valko, and Rémi Munos · 2025
Closest in time.
On the design of kl-regularized policy gradient algorithms for llm reasoning
Yifan Zhang, Yifeng Liu, Huizhuo Yuan, Yang Yuan, Quanquan Gu, and Andrew C Yao · 2025
Closest in time.
d1: Scaling reasoning in diffusion large language models via reinforcement learning
Siyan Zhao, Devaansh Gupta, Qinqing Zheng, and Aditya Grover · 2025
Closest in time.