English
Related papers

Related papers: Learning from the Right Rollouts: Data Attribution…

200 papers

Proximal Policy Optimization (PPO) is among the most widely used algorithms in reinforcement learning, which achieves state-of-the-art performance in many challenging problems. The keys to its success are the reliable policy updates through…

Machine Learning · Computer Science 2021-07-02 Mónika Farsang , Luca Szegletes

This paper provides a self-contained, from-scratch, exposition of key algorithms for instruction tuning of models: SFT, Rejection Sampling, REINFORCE, Trust Region Policy Optimization (TRPO), Proximal Policy Optimization (PPO), Group…

Computation and Language · Computer Science 2025-10-22 Rohit Patel

Existing LLM-based policy optimizers see only scalar rewards: that a policy scored 0.45, but not whether the agent got stuck in a loop, fell into a hole on the third step, or performed well on 19 out of 20 rollouts and failed…

Machine Learning · Computer Science 2026-05-12 Rahaf Abu Hara , Vaibbhav Murarri , Claudio Zito

While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information.…

Artificial Intelligence · Computer Science 2024-10-30 Long Tan Le , Han Shu , Tung-Anh Nguyen , Choong Seon Hong , Nguyen H. Tran

DPO (Direct Preference Optimization) has become a widely used offline preference optimization algorithm due to its simplicity and training stability. However, DPO is prone to overfitting and collapse. To address these challenges, we propose…

Machine Learning · Computer Science 2025-08-26 Rui Wang , Qianguo Sun , Chao Song , Junlong Wu , Tianrong Chen , Zhiyun Zeng , Yu Li

Instruction-fine-tuned large language models (LLMs) under 14B parameters continue to underperform on natural language understanding (NLU) tasks, often trailing smaller models like BERT-base on benchmarks such as GLUE and SuperGLUE.…

Computation and Language · Computer Science 2025-09-29 Bokai Hu , Sai Ashish Somayajula , Xin Pan , Pengtao Xie

Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle in domains like math and coding. Reinforcement learning (RL)-based post-training methods,…

Computation and Language · Computer Science 2026-05-19 Zhichao Wang , Kiran Ramnath , Bin Bi , Shiva Kumar Pentyala , Sougata Chaudhuri , Shubham Mehrotra , Zixu , Zhu , Xiang-Bo Mao , Sitaram Asur , Na , Cheng

While Retrieval-Augmented Generation (RAG) has exhibited promise in utilizing external knowledge, its generation process heavily depends on the quality and accuracy of the retrieved context. Large language models (LLMs) struggle to evaluate…

Computation and Language · Computer Science 2025-10-13 Shi-Qi Yan , Quan Liu , Zhen-Hua Ling

Reinforcement learning (RL) is widely used for post-training large language models (LLMs) in code editing, where group-relative methods, such as GRPO, are popular due to their critic-free and normalized advantage estimation. However, in…

Machine Learning · Computer Science 2026-01-09 Jianqing Zhang , Zhezheng Hao , Wei Xia , Hande Dong , Hong Wang , Chenxing Wei , Yuyan Zhou , Yubin Qi , Qiang Lin , Jian Cao

Large Language Models (LLMs) can acquire extensive world knowledge through pre-training on large corpora. However, due to exposure to low-quality data, LLMs may exhibit harmful behavior without aligning with human values. The dominant…

Machine Learning · Computer Science 2023-10-11 Tianhao Wu , Banghua Zhu , Ruoyu Zhang , Zhaojin Wen , Kannan Ramchandran , Jiantao Jiao

Training a reinforcement learning agent on-policy means collecting fresh experience at every update, and that experience comes with a hidden problem. Each state in a rollout is the direct output of the previous one, causally chained…

Machine Learning · Computer Science 2026-05-27 Ajhesh Basnet

Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in this setting due to the instability of temporal credit…

Artificial Intelligence · Computer Science 2026-04-13 Tianyi Wang , Yixia Li , Long Li , Yibiao Chen , Shaohan Huang , Yun Chen , Peng Li , Yang Liu , Guanhua Chen

Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over…

Artificial Intelligence · Computer Science 2026-04-23 Darsh Kachroo , Adriana Caraeni , Arjun Prasaath Anbazhagan , Brennan Lagasse , Kevin Zhu

Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates significant potential in enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing RLVR methods are often constrained by issues such as…

Artificial Intelligence · Computer Science 2026-01-14 Jinpeng Wang , Chao Li , Ting Ye , Mengyuan Zhang , Wei Liu , Jian Luan

While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models.…

Existing Reinforcement Learning from Verifiable Rewards (RLVR) methods, such as Group Relative Policy Optimization (GRPO), have achieved remarkable progress in improving the reasoning capabilities of Large Reasoning Models (LRMs). However,…

Machine Learning · Computer Science 2026-04-16 Hsiu-Yuan Huang , Chenming Tang , Weijie Liu , Clive Bai , Saiyong Yang , Yunfang Wu

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

Reinforcement Learning (RL) in partially observable environments poses significant challenges due to the complexity of learning under uncertainty. While additional information, such as that available in simulations, can enhance training,…

Machine Learning · Computer Science 2026-03-16 Yueheng Li , Guangming Xie , Zongqing Lu

Multi-turn human-AI collaboration is fundamental to deploying interactive services such as adaptive tutoring, conversational recommendation, and professional consultation. However, optimizing these interactions via reinforcement learning is…

Machine Learning · Computer Science 2026-03-26 Haoyu Wang , Yuxin Chen , Liang Luo , Buyun Zhang , Ellie Dingqiao Wen , Pan Li

Proximal Policy Optimization (PPO) has been broadly applied to robotics learning, showcasing stable training performance. However, the fixed clipping bound setting may limit the performance of PPO. Specifically, there is no theoretical…

Machine Learning · Computer Science 2024-11-07 Ziqi Zhang , Jingzehua Xu , Zifeng Zhuang , Hongyin Zhang , Jinxin Liu , Donglin wang , Shuai Zhang