English
Related papers

Related papers: Beyond Negative Rollouts: Positive-Only Policy Opt…

200 papers

Reinforcement Learning with Verifiable Rewards (RLVR) offers a robust mechanism for enhancing mathematical reasoning in large models. However, we identify a systematic lack of emphasis on more challenging questions in existing methods from…

Artificial Intelligence · Computer Science 2026-01-29 Yanqi Dai , Yuxiang Ji , Xiao Zhang , Yong Wang , Xiangxiang Chu , Zhiwu Lu

Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of large language models (LLMs), but it often suffers from \textit{restricted exploration}, where the policy rapidly concentrates on a…

Computation and Language · Computer Science 2026-05-13 Hengrui Gu , Xiaotian Han , Yujing Bian , Feiyi Wang , Kaixiong Zhou

Reinforcement learning algorithms such as GRPO have driven recent advances in large language model (LLM) reasoning. While scaling the number of rollouts stabilizes training, existing approaches suffer from limited exploration on challenging…

Machine Learning · Computer Science 2026-05-26 Udbhav Bamba , Minghao Fang , Yifan Yu , Haizhong Zheng , Fan Lai

Expressive generative models have advanced robotic manipulation by capturing complex, multi-modal action distributions over temporally extended trajectories. However, fine-tuning these policies via RL remains challenging due to instability…

Robotics · Computer Science 2026-04-03 Yuhui Chen , Haoran Li , Zhennan Jiang , Yuxing Qin , Yuxuan Wan , Weiheng Liu , Dongbin Zhao

While Reinforcement Learning from Verifiable Rewards (RLVR) has advanced reasoning in Large Vision-Language Models (LVLMs), prevailing frameworks suffer from a foundational methodological flaw: by distributing identical advantages across…

Artificial Intelligence · Computer Science 2026-04-09 Zekai Ye , Qiming Li , Xiaocheng Feng , Ruihan Chen , Ziming Li , Haoyu Ren , Kun Chen , Dandan Tu , Bing Qin

Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding a principled recipe for designing alignment losses. However,…

Machine Learning · Computer Science 2026-05-12 Rajdeep Haldar , Lantao Mei , Guang Lin , Yue Xing , Qifan Song

Reinforcement learning (RL) has proven remarkably effective at improving the accuracy of language models in verifiable and deterministic domains like mathematics. Here, we examine if current RL methods are also effective at optimizing…

Machine Learning · Computer Science 2025-08-19 Michael Bereket , Jure Leskovec

Latent reasoning offers a more efficient alternative to explicit reasoning by compressing intermediate reasoning into continuous representations and substantially shortening reasoning chains. However, existing latent reasoning methods…

Machine Learning · Computer Science 2026-05-01 Jingcheng Deng , Zihao Wei , Liang Pang , Junhong Wu , Shicheng Xu , Zenghao Duan , Huawei Shen

Adapting large language models (LLMs) for specific tasks usually involves fine-tuning through reinforcement learning with human feedback (RLHF) on preference data. While these data often come from diverse labelers' groups (e.g., different…

Computation and Language · Computer Science 2024-05-31 Shyam Sundhar Ramesh , Yifan Hu , Iason Chaimalas , Viraj Mehta , Pier Giuseppe Sessa , Haitham Bou Ammar , Ilija Bogunovic

Group Relative Policy Optimization (GRPO) has significantly enhanced the reasoning capability of large language models by optimizing the arithmetic mean of token-level rewards. Unfortunately, GRPO is observed to suffer from unstable policy…

Computation and Language · Computer Science 2025-10-21 Yuzhong Zhao , Yue Liu , Junpeng Liu , Jingye Chen , Xun Wu , Yaru Hao , Tengchao Lv , Shaohan Huang , Lei Cui , Qixiang Ye , Fang Wan , Furu Wei

Recent advances in constrained reinforcement learning (RL) have endowed reinforcement learning with certain safety guarantees. However, deploying existing constrained RL algorithms in continuous control tasks with general hard constraints…

Machine Learning · Computer Science 2023-12-22 Shutong Ding , Jingya Wang , Yali Du , Ye Shi

Reinforcement Learning with Verifiable Rewards (RLVR) has become the standard paradigm for LLM mathematical reasoning, with Group Relative Policy Optimization (GRPO) serving as the dominant algorithm. We identify two overlooked…

Machine Learning · Computer Science 2026-05-13 Mingxiong Lin , Zhangquan Gong , Maowen Tang , Qian Li , Chuangchuang Wang , Jian Ma , Sutian Huang , Kai Tang , Haonan Lu

Search agents extend Large Language Models (LLMs) beyond static parametric knowledge by enabling access to up-to-date and long-tail information unavailable during pretraining. While reinforcement learning has been widely adopted for…

Machine Learning · Computer Science 2026-04-21 Junzhe Wang , Zhiheng Xi , Yajie Yang , Hao Luo , Shihan Dou , Tao Gui , Qi Zhang

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

Group Relative Policy Optimization (GRPO) has recently emerged as a practical recipe for aligning large language models with verifiable objectives. However, under sparse terminal rewards, GRPO often stalls because rollouts within a group…

Machine Learning · Computer Science 2026-02-04 Baohao Liao , Hanze Dong , Xinxing Xu , Christof Monz , Jiang Bian

Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), as the widely employed policy based reinforcement learning (RL) methods, are prone to converge to a sub-optimal solution as they limit the policy representation…

Machine Learning · Computer Science 2020-06-16 Jun Song , Chaoyue Zhao

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

Group Relative Policy Optimization (GRPO) has emerged as a powerful algorithm for improving the reasoning capabilities of language models, but often fails to improve small models due to sparse rewards on difficult tasks. Existing works…

Machine Learning · Computer Science 2026-05-12 Soo Min Kwon , Ziteng Sun , Ananda Theertha Suresh , Himanshu Jain , Sanjiv Kumar

GRPO is a standard approach to endowing pretrained LLMs with reasoning capabilities. It estimates the advantage of an outcome from a group of $K$ outcomes, and promotes those with positive advantages inside a trust region. Since GRPO…

Machine Learning · Computer Science 2026-02-02 Wenzheng Zhang , Karl Stratos

Proximal Policy Optimization (PPO) dominates reinforcement learning and LLM alignment but relies on a "hard clipping" mechanism that discards valuable gradients. Conversely, unconstrained methods like SPO expose the optimization to…

Artificial Intelligence · Computer Science 2026-05-07 Yiheng Zhang , Yiming Wang , Kaiyan Zhao , Zhenglin Wan , Jiayu Chen , Leong Hou U