VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks

• URL: http://arxiv.org/abs/2504.05118v3
• Date: Fri, 11 Apr 2025 02:54:58 GMT
• Title: VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks
• Authors: Yu Yue, Yufeng Yuan, Qiying Yu, Xiaochen Zuo, Ruofei Zhu, Wenyuan Xu, Jiaze Chen, Chengyi Wang, TianTian Fan, Zhengyin Du, Xiangpeng Wei, Xiangyu Yu, Gaohong Liu, Juncai Liu, Lingjun Liu, Haibin Lin, Zhiqi Lin, Bole Ma, Chi Zhang, Mofan Zhang, Wang Zhang, Hang Zhu, Ru Zhang, Xin Liu, Mingxuan Wang, Yonghui Wu, Lin Yan,
• Abstract summary: We present VAPO, a novel framework tailored for reasoning models within the value-based paradigm.<n>VAPO attains a state-of-the-art score of $mathbf60.4$.<n>In direct comparison under identical experimental settings, VAPO outperforms the previously reported results of DeepSeek-R1-Zero-Qwen-32B and DAPO by more than 10 points.
• Score: 49.0793012627959
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present VAPO, Value-based Augmented Proximal Policy Optimization framework for reasoning models., a novel framework tailored for reasoning models within the value-based paradigm. Benchmarked the AIME 2024 dataset, VAPO, built on the Qwen 32B pre-trained model, attains a state-of-the-art score of $\mathbf{60.4}$. In direct comparison under identical experimental settings, VAPO outperforms the previously reported results of DeepSeek-R1-Zero-Qwen-32B and DAPO by more than 10 points. The training process of VAPO stands out for its stability and efficiency. It reaches state-of-the-art performance within a mere 5,000 steps. Moreover, across multiple independent runs, no training crashes occur, underscoring its reliability. This research delves into long chain-of-thought (long-CoT) reasoning using a value-based reinforcement learning framework. We pinpoint three key challenges that plague value-based methods: value model bias, the presence of heterogeneous sequence lengths, and the sparsity of reward signals. Through systematic design, VAPO offers an integrated solution that effectively alleviates these challenges, enabling enhanced performance in long-CoT reasoning tasks.

Related papers

• Lean and Mean: Decoupled Value Policy Optimization with Global Value Guidance [52.65461207786633]
  Policy-based Reinforcement Learning from Human Feedback is essential for aligning large language models with human preferences. It requires joint training of an actor and critic with a pretrained, fixed reward model for guidance. We propose textbfDecoupled Value Policy Optimization (DVPO), a lean framework that replaces traditional reward modeling with a pretrained emphglobal value model (GVM)
  arXiv  Detail & Related papers  (2025-02-24T08:11:33Z)
• Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning [65.2421542320293]
  Reasoning abilities are crucial components of general intelligence.<n>Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning tasks.<n>This paper proposes a new RL framework, termed OREAL, to pursue the performance limit that can be achieved through textbfOutcome textbfREwtextbfArd-based reinforcement textbfLearning for mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2025-02-10T18:57:29Z)
• FORLAPS: An Innovative Data-Driven Reinforcement Learning Approach for Prescriptive Process Monitoring [3.4437362489150254]
  This study introduces an innovative evaluation model, benchmarking its performance against earlier works using nine publicly available datasets.<n>The proposed model, FORLAPS, demonstrated exceptional performance, outperforming existing state-of-the-art approaches in suggesting the most optimal policies or predicting the best next activities within a process trace.
  arXiv  Detail & Related papers  (2025-01-17T20:31:35Z)
• Batch-in-Batch: a new adversarial training framework for initial perturbation and sample selection [9.241737058291823]
  Adrial training methods generate independent initial perturbation for adversarial samples from a simple uniform distribution. We propose a simple yet effective training framework called Batch-in-Batch to enhance models. We show that models trained within the BB framework consistently have higher adversarial accuracy across various adversarial settings.
  arXiv  Detail & Related papers  (2024-06-06T13:34:43Z)
• Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving [55.93813178692077]
  We present RoboBEV, an extensive benchmark suite designed to evaluate the resilience of BEV algorithms.<n>We assess 33 state-of-the-art BEV-based perception models spanning tasks like detection, map segmentation, depth estimation, and occupancy prediction.<n>Our experimental results also underline the efficacy of strategies like pre-training and depth-free BEV transformations in enhancing robustness against out-of-distribution data.
  arXiv  Detail & Related papers  (2024-05-27T17:59:39Z)
• Learning Off-policy with Model-based Intrinsic Motivation For Active Online Exploration [15.463313629574111]
  This paper investigates how to achieve sample-efficient exploration in continuous control tasks. We introduce an RL algorithm that incorporates a predictive model and off-policy learning elements. We derive an intrinsic reward without incurring parameters overhead.
  arXiv  Detail & Related papers  (2024-03-31T11:39:11Z)
• Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization [53.04697800214848]
  Adversarial Training (AT) is pivotal in fortifying the robustness of deep learning models. AT methods, relying on direct iterative updates for target model's defense, frequently encounter obstacles such as unstable training and catastrophic overfitting. We present a general proxy guided defense framework, LAST' (bf Learn from the Pbf ast)
  arXiv  Detail & Related papers  (2023-10-19T13:13:41Z)
• Efficient Epistemic Uncertainty Estimation in Regression Ensemble Models Using Pairwise-Distance Estimators [21.098866735156207]
  Pairwise-distance estimators (PaiDEs) establish bounds on entropy. Unlike sample-based Monte Carlo estimators, PaiDEs exhibit a remarkable capability to estimate epistemic uncertainty at speeds up to 100 times faster. We compare our approach to existing active learning methods and find that our approach outperforms on high-dimensional regression tasks.
  arXiv  Detail & Related papers  (2023-08-25T17:13:42Z)
• Revisiting DETR Pre-training for Object Detection [24.372444866927538]
  We investigate the shortcomings of DETReg in enhancing the performance of robust DETR-based models under full data conditions. We employ an optimized approach named Simple Self-training which leads to marked enhancements through the combination of an improved box predictor and the Objects$365$ benchmark. The culmination of these endeavors results in a remarkable AP score of $59.3%$ on the COCO val set, outperforming $mathcalH$-Deformable-DETR + Swin-L without pre-training by $1.4%$.
  arXiv  Detail & Related papers  (2023-08-02T17:39:30Z)
• COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarization [84.70895015194188]
  We propose a Contrastive Learning based re-ranking framework for one-stage summarization called COLO. COLO boosts the extractive and abstractive results of one-stage systems on CNN/DailyMail benchmark to 44.58 and 46.33 ROUGE-1 score.
  arXiv  Detail & Related papers  (2022-09-29T06:11:21Z)
• Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference [119.19779637025444]
  Deep networks were recently suggested to face the odds between accuracy (on clean natural images) and robustness (on adversarially perturbed images) This paper studies multi-exit networks associated with input-adaptive inference, showing their strong promise in achieving a "sweet point" in cooptimizing model accuracy, robustness and efficiency.
  arXiv  Detail & Related papers  (2020-02-24T00:40:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.