English
Related papers

Related papers: Directional-Clamp PPO

200 papers

The last year has witnessed the rapid progress of large language models (LLMs) across diverse domains. Among them, CodeLLMs have garnered particular attention because they can not only assist in completing various programming tasks but also…

Artificial Intelligence · Computer Science 2024-10-25 Yibo Miao , Bofei Gao , Shanghaoran Quan , Junyang Lin , Daoguang Zan , Jiaheng Liu , Jian Yang , Tianyu Liu , Zhijie Deng

Direct Preference Optimization (DPO) has proven effective at improving the performance of large language models (LLMs) on downstream tasks such as reasoning and alignment. In this work, we propose Step-Controlled DPO (SCDPO), a method for…

Computation and Language · Computer Science 2024-07-16 Zimu Lu , Aojun Zhou , Ke Wang , Houxing Ren , Weikang Shi , Junting Pan , Mingjie Zhan , Hongsheng Li

Direct Preference Optimization (DPO) has become a widely used training method for the instruction fine-tuning of large language models (LLMs). In this work, we explore an under-investigated aspect of DPO - its dependency on the reference…

Computation and Language · Computer Science 2024-08-23 Yixin Liu , Pengfei Liu , Arman Cohan

Much of the recent success of deep reinforcement learning has been driven by regularized policy optimization (RPO) algorithms with strong performance across multiple domains. In this family of methods, agents are trained to maximize…

Machine Learning · Computer Science 2022-03-24 Ted Moskovitz , Michael Arbel , Jack Parker-Holder , Aldo Pacchiano

Safe Reinforcement Learning (RL) often faces significant issues such as constraint violations and instability, necessitating the use of constrained policy optimization, which seeks optimal policies while ensuring adherence to specific…

Machine Learning · Computer Science 2025-08-07 Ning Yang , Pengyu Wang , Guoqing Liu , Haifeng Zhang , Pin Lv , Jun Wang

Proximal constraints are fundamental to the stability of the Large Language Model reinforcement learning. While the canonical clipping mechanism in PPO serves as an efficient surrogate for trust regions, we identify a critical bottleneck:…

Machine Learning · Computer Science 2026-03-06 Yuan Li , Bo Wang , Yufei Gao , Yuqian Yao , Xinyuan Wang , Zhangyue Yin , Xipeng Qiu

Policy gradient methods usually rely on entropy regularization to prevent premature convergence. However, maximizing entropy indiscriminately pushes the policy towards a uniform distribution, often overriding the reward signal if not…

Machine Learning · Computer Science 2026-03-06 Luca Serfilippi , Giorgio Franceschelli , Antonio Corradi , Mirco Musolesi

Despite Proximal Policy Optimization (PPO) dominating policy gradient methods -- from robotic control to game AI -- its static trust region forces a brittle trade-off: aggressive clipping stifles early exploration, while late-stage updates…

Machine Learning · Computer Science 2025-05-26 Ben Rahman

Proximal policy optimization (PPO) is one of the most popular state-of-the-art on-policy algorithms that has become a standard baseline in modern reinforcement learning with applications in numerous fields. Though it delivers stable…

Machine Learning · Computer Science 2025-02-25 Qisai Liu , Zhanhong Jiang , Hsin-Jung Yang , Mahsa Khosravi , Joshua R. Waite , Soumik Sarkar

Reinforcement learning has become central to post-training large language models, yet dominant algorithms rely on clipping mechanisms that introduce optimization issues at scale, including zero-gradient regions, reward hacking, and training…

Machine Learning · Computer Science 2026-02-02 Ömer Veysel Çağatan , Barış Akgün , Gözde Gül Şahin , Xuandong Zhao

Policy optimization methods are popular reinforcement learning algorithms, because their incremental and on-policy nature makes them more stable than the value-based counterparts. However, the same properties also make them slow to converge…

Machine Learning · Computer Science 2021-07-01 Andrea Zanette , Ching-An Cheng , Alekh Agarwal

Efficient preference optimization algorithms such as Direct Preference Optimization (DPO) have become a popular approach in aligning large language models (LLMs) with human preferences. These algorithms implicitly treat the LLM as a reward…

Computation and Language · Computer Science 2025-07-29 Tong Liu , Xiao Yu , Wenxuan Zhou , Jindong Gu , Volker Tresp

Traditional RL algorithms like Proximal Policy Optimization (PPO) typically train on the entire rollout buffer, operating under the assumption that all generated episodes provide a beneficial optimization signal. However, these episodes…

Machine Learning · Computer Science 2026-04-03 Dong Shu , Denghui Zhang , Jessica Hullman

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

Mirror descent (MD), a well-known first-order method in constrained convex optimization, has recently been shown as an important tool to analyze trust-region algorithms in reinforcement learning (RL). However, there remains a considerable…

Machine Learning · Computer Science 2021-06-08 Manan Tomar , Lior Shani , Yonathan Efroni , Mohammad Ghavamzadeh

Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement…

Computation and Language · Computer Science 2024-12-10 Junru Lu , Jiazheng Li , Siyu An , Meng Zhao , Yulan He , Di Yin , Xing Sun

Recent advances in reinforcement learning for foundation models, such as Group Relative Policy Optimization (GRPO), have significantly improved the performance of foundation models on reasoning tasks. Notably, the advantage function serves…

Artificial Intelligence · Computer Science 2025-09-26 Wenke Huang , Quan Zhang , Yiyang Fang , Jian Liang , Xuankun Rong , Huanjin Yao , Guancheng Wan , Ke Liang , Wenwen He , Mingjun Li , Leszek Rutkowski , Mang Ye , Bo Du , Dacheng Tao

Standard on-policy reinforcement learning relies on heuristic clipping to enforce trust regions, but this mechanism imposes a severe cost by indiscriminately truncating high-return yet high-divergence updates. We demonstrate that explicitly…

Machine Learning · Computer Science 2026-05-27 Yu Luo , Shuo Han , Yihan Hu , Lei Lv , Huaping Liu , Fuchun Sun , Jianye Hao , Dong Li

Reinforcement learning with verifiable rewards (RLVR), due to the deterministic verification, becomes a dominant paradigm for enhancing the reasoning ability of large language models (LLMs). The community witnesses the rapid change from the…

Computation and Language · Computer Science 2026-05-08 Mingwei Xu , Hao Fang

Direct Preference Optimization (DPO) have emerged as a popular method for aligning Large Language Models (LLMs) with human preferences. While DPO effectively preserves the relative ordering between chosen and rejected responses through…

Computation and Language · Computer Science 2025-06-05 Lin Sun , Chuang Liu , Peng Liu , Bingyang Li , Weijia Lu , Ning Wu
‹ Prev 1 3 4 5 6 7 10 Next ›