English
Related papers

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

200 papers

Group distributionally robust optimization (GDRO) aims to develop models that perform well across $m$ distributions simultaneously. Existing GDRO algorithms can only process a fixed number of samples per iteration, either 1 or $m$, and…

Machine Learning · Computer Science 2025-05-22 Haomin Bai , Dingzhi Yu , Shuai Li , Haipeng Luo , Lijun Zhang

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising approach to improve the reasoning abilities of Large Language Models (LLMs). Among RLVR algorithms, Group Relative Policy Optimization (GRPO) and its variants…

Artificial Intelligence · Computer Science 2026-04-21 Zhaokang Liao , Yingguo Gao , Yi Yang , Yongheng Hu , Jingting Ding

This paper introduces Completion Pruning Policy Optimization (CPPO) to accelerate the training of reasoning models based on Group Relative Policy Optimization (GRPO). GRPO, while effective, incurs high training costs due to the need to…

Artificial Intelligence · Computer Science 2025-11-11 Zhihang Lin , Mingbao Lin , Yuan Xie , Rongrong Ji

Fine-tuning large language models (LLMs) for reasoning tasks using reinforcement learning methods like Group Relative Policy Optimization (GRPO) is computationally expensive. To address this, we propose a predictive framework that models…

Machine Learning · Computer Science 2026-03-23 Datta Nimmaturi , Vaishnavi Bhargava , Rajat Ghosh , Johnu George , Debojyoti Dutta

Scaling deep reinforcement learning networks is challenging and often results in degraded performance, yet the root causes of this failure mode remain poorly understood. Several recent works have proposed mechanisms to address this, but…

In learning from demonstrations, many generative models of trajectories make simplifying assumptions of independence. Correctness is sacrificed in the name of tractability and speed of the learning phase. The ignored dependencies, which…

Robotics · Computer Science 2020-11-09 Emmanuel Pignat , Hakan Girgin , Sylvain Calinon

Group Relative Policy Optimization (GRPO) is effective for training language models on complex reasoning. However, since the objective is defined relative to a group of sampled trajectories, extended deliberation can create more chances to…

This paper introduces Group Sequence Policy Optimization (GSPO), our stable, efficient, and performant reinforcement learning algorithm for training large language models. Unlike previous algorithms that adopt token-level importance ratios,…

Machine Learning · Computer Science 2025-07-29 Chujie Zheng , Shixuan Liu , Mingze Li , Xiong-Hui Chen , Bowen Yu , Chang Gao , Kai Dang , Yuqiong Liu , Rui Men , An Yang , Jingren Zhou , Junyang Lin

Regularized estimators in the context of group variables have been applied successfully in model and feature selection in order to preserve interpretability. We formulate a Distributionally Robust Optimization (DRO) problem which recovers…

Statistics Theory · Mathematics 2017-05-12 Jose Blanchet , Yang Kang

Safe and feasible trajectory planning is critical for real-world autonomous driving systems. However, existing learning-based planners rely heavily on expert demonstrations, which not only lack explicit safety awareness but also risk…

Robotics · Computer Science 2025-09-29 Xiaolong Tang , Meina Kan , Shiguang Shan , Xilin Chen

Group Relative Policy Optimization (GRPO) is a powerful technique for aligning generative models, but its effectiveness is bottlenecked by the conflict between large group sizes and prohibitive computational costs. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2025-12-18 Shiran Ge , Chenyi Huang , Yuang Ai , Qihang Fan , Huaibo Huang , Ran He

Distributionally robust optimization (DRO) provides a framework for training machine learning models that are able to perform well on a collection of related data distributions (the "uncertainty set"). This is done by solving a min-max…

Machine Learning · Computer Science 2021-04-01 Paul Michel , Tatsunori Hashimoto , Graham Neubig

In safe reinforcement learning (SRL) problems, an agent explores the environment to maximize an expected total reward and meanwhile avoids violation of certain constraints on a number of expected total costs. In general, such SRL problems…

Machine Learning · Computer Science 2021-06-01 Tengyu Xu , Yingbin Liang , Guanghui Lan

For all its successes, Reinforcement Learning (RL) still struggles to deliver formal guarantees on the closed-loop behavior of the learned policy. Among other things, guaranteeing the safety of RL with respect to safety-critical systems is…

Systems and Control · Electrical Eng. & Systems 2020-04-03 Sebastien Gros , Mario Zanon , Alberto Bemporad

Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed a leap in Large Language Model (LLM) reasoning, yet its optimization dynamics remain fragile. Standard algorithms like GRPO enforce stability via "hard clipping", which…

Machine Learning · Computer Science 2026-04-21 Xiaoliang Fu , Jiaye Lin , Yangyi Fang , Chaowen Hu , Cong Qin , Zekai Shao , Binbin Zheng , Lu Pan , Ke Zeng

Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO) are among the most successful policy gradient approaches in deep reinforcement learning (RL). While these methods achieve state-of-the-art performance across a…

Machine Learning · Computer Science 2020-06-22 Ahmed Touati , Amy Zhang , Joelle Pineau , Pascal Vincent

Group Relative Policy Optimization (GRPO) has become the dominant method for reinforcement learning with verifiable rewards in large language models, but it suffers from two critical limitations: gradient vanishing and diversity collapse.…

Machine Learning · Computer Science 2026-05-20 Khiem Le , Phuc Nguyen , Youssef Mroueh , Chi-Heng Lin , Shangqian Gao , Ting Hua , Nitesh V. Chawla

Many of the successes of machine learning are based on minimizing an averaged loss function. However, it is well-known that this paradigm suffers from robustness issues that hinder its applicability in safety-critical domains. These issues…

Machine Learning · Computer Science 2022-06-09 Alexander Robey , Luiz F. O. Chamon , George J. Pappas , Hamed Hassani

Post-training has significantly enhanced the reasoning capability of Large Reasoning Models (LRMs), especially with Reinforcement Learning (RL) like Group Relative Policy Optimization (GRPO). However, GRPO-style RL methods in multi-domain…

Computation and Language · Computer Science 2026-05-26 Zongji Yu , Wenshui Luo , Yiliu Sun , Hao Fang , Runmin Cong , Chaochao Lu , Chen Gong

Advanced test-time computing strategies are essential for scaling reasoning models, but their effectiveness is capped by the models' poor self-evaluation. We propose a pairwise Explanatory Verifier, trained via reinforcement learning…

Artificial Intelligence · Computer Science 2025-09-25 Anisha Garg , Engin Tekin , Yash More , David Bick , Nishit Neema , Ganesh Venkatesh