English
Related papers

Related papers: On the Plasticity and Stability for Post-Training …

200 papers

Group-Relative Policy Optimization (GRPO) is a key technique for training large reasoning models, yet it suffers from a critical vulnerability: the \emph{Think-Answer Mismatch}, where noisy reward signals corrupt the learning process. This…

Machine Learning · Computer Science 2025-08-11 Si Shen , Peijun Shen , Wenhua Zhao , Danhao Zhu

We consider the challenge of finding a deterministic policy for a Markov decision process that uniformly (in all states) maximizes one reward subject to a probabilistic constraint over a different reward. Existing solutions do not fully…

Machine Learning · Computer Science 2022-01-21 Jaeyoung Lee , Sean Sedwards , Krzysztof Czarnecki

In order to model risk aversion in reinforcement learning, an emerging line of research adapts familiar algorithms to optimize coherent risk functionals, a class that includes conditional value-at-risk (CVaR). Because optimizing the…

Machine Learning · Computer Science 2021-03-09 Audrey Huang , Liu Leqi , Zachary C. Lipton , Kamyar Azizzadenesheli

Training large language models (LLMs) with reinforcement learning (RL) methods such as PPO and GRPO commonly relies on ratio clipping to stabilise updates. While effective at preventing instability, clipping discards information, introduces…

Machine Learning · Computer Science 2026-02-02 Madeleine Dwyer , Adam Sobey , Adriane Chapman

Image captioning tasks usually use two-stage training to complete model optimization. The first stage uses cross-entropy as the loss function for optimization, and the second stage uses self-critical sequence training (SCST) for…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Xu Liang

Recent advances in rule-based reinforcement learning (RL) have significantly improved the reasoning capability of language models (LMs) with rule-based rewards. However, existing RL methods -- such as GRPO, REINFORCE++, and RLOO -- often…

Machine Learning · Computer Science 2025-05-20 Zongkai Liu , Fanqing Meng , Lingxiao Du , Zhixiang Zhou , Chao Yu , Wenqi Shao , Qiaosheng Zhang

Large reasoning models (LRMs) generate intermediate reasoning traces before producing final answers, yielding strong gains on multi-step and mathematical tasks. Yet aligning LRMs with human preferences, a crucial prerequisite for model…

Machine Learning · Computer Science 2025-10-07 Mingkang Zhu , Xi Chen , Bei Yu , Hengshuang Zhao , Jiaya Jia

Post-training paradigms for Large Language Models (LLMs), primarily Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), face a fundamental dilemma: SFT provides stability (low variance) but suffers from high fitting bias, while RL…

Machine Learning · Computer Science 2026-04-13 Taojie Zhu , Dongyang Xu , Ding Zou , Sen Zhao , Qiaobo Hao , Zhiguo Yang , Yonghong He

Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we revisit the traditional Policy Gradient (PG) mechanism and…

Machine Learning · Computer Science 2026-02-04 Xiangxiang Chu , Hailang Huang , Xiao Zhang , Fei Wei , Yong Wang

The recent remarkable progress of deep reinforcement learning (DRL) stands on regularization of policy for stable and efficient learning. A popular method, named proximal policy optimization (PPO), has been introduced for this purpose. PPO…

Machine Learning · Computer Science 2023-07-04 Taisuke Kobayashi

Informed and robust decision making in the face of uncertainty is critical for robots that perform physical tasks alongside people. We formulate this as Bayesian Reinforcement Learning over latent Markov Decision Processes (MDPs). While…

Robotics · Computer Science 2020-02-11 Gilwoo Lee , Brian Hou , Sanjiban Choudhury , Siddhartha S. Srinivasa

ReParameterization (RP) Policy Gradient Methods (PGMs) have been widely adopted for continuous control tasks in robotics and computer graphics. However, recent studies have revealed that, when applied to long-term reinforcement learning…

Machine Learning · Computer Science 2023-11-01 Shenao Zhang , Boyi Liu , Zhaoran Wang , Tuo Zhao

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

Recent advances in large language models (LLMs) have broadened their applicability across diverse tasks, yet specialized domains still require targeted post training. Among existing methods, Group Relative Policy Optimization (GRPO) stands…

Machine Learning · Computer Science 2025-08-08 Ziyin Gu , Jingyao Wang , Ran Zuo , Chuxiong Sun , Zeen Song , Changwen Zheng , Wenwen Qiang

Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs due to its extensive group-based sampling requirement. While recent selective data utilization methods can mitigate this…

Machine Learning · Computer Science 2026-03-05 Haodong Zhu , Yangyang Ren , Yanjing Li , Mingbao Lin , Linlin Yang , Xuhui Liu , Xiantong Zhen , Haiguang Liu , Baochang Zhang

Uncertainties in transition dynamics pose a critical challenge in reinforcement learning (RL), often resulting in performance degradation of trained policies when deployed on hardware. Many robust RL approaches follow two strategies:…

Machine Learning · Computer Science 2026-01-29 Xulin Chen , Ruipeng Liu , Zhenyu Gan , Garrett E. Katz

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an important paradigm for unlocking reasoning capabilities in large language models, exemplified by the success of OpenAI o1 and DeepSeek-R1. Currently, Group Relative…

Machine Learning · Computer Science 2026-01-08 Shijie Zhang , Kevin Zhang , Zheyuan Gu , Xiang Guo , Rujun Guo , Shaoyu Liu , Guanjun Jiang , Xiaozhao Wang

By leveraging differentiable dynamics, Reparameterization Policy Gradient (RPG) achieves high sample efficiency. However, current approaches are hindered by two critical limitations: the under-utilization of computationally expensive…

Machine Learning · Computer Science 2026-02-09 Hai Zhong , Xun Wang , Zhuoran Li , Longbo Huang

Reinforcement learning (RL) is effective in enhancing the accuracy of large language models in complex reasoning tasks. Existing RL policy optimization frameworks rely on final-answer correctness as feedback signals and rarely capture the…

Artificial Intelligence · Computer Science 2026-04-13 Jinghan Zhang , Fengran Mo , Tharindu Cyril Weerasooriya , Ruimin Dai , Xiaoyan Han , Yanjie Fu , Dakuo Wang , Kunpeng Liu

Group Relative Policy Optimization (GRPO) has been a key driver of recent progress in reinforcement learning with verifiable rewards (RLVR) for large language models, but it is typically trained in a low-staleness, near-on-policy regime…

Machine Learning · Computer Science 2026-05-19 Minghao Tian , Yunfei Xie , Chen Wei