PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning
Audio is streamed directly from the publisher (media.transistor.fm) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
🤗 Upvotes: 21 | cs.LG, cs.AI
Authors:
Wenfeng Feng, Penghong Zhao, Guochao Jiang, Chuzhan Hao, Yuewei Zhang, Hao Wang
Title:
PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning
Arxiv:
http://arxiv.org/abs/2508.21104v1
Abstract:
Critic-free reinforcement learning methods, particularly group policies, have attracted considerable attention for their efficiency in complex tasks. However, these methods rely heavily on multiple sampling and comparisons within the policy to estimate advantage, which may cause the policy to fall into local optimum and increase computational cost. To address these issues, we propose PVPO, an efficient reinforcement learning method enhanced by an advantage reference anchor and data pre-sampling. Specifically, we use the reference model to rollout in advance and employ the calculated reward score as a reference anchor. Our approach effectively corrects the cumulative bias introduced by intra-group comparisons and significantly reduces reliance on the number of rollouts. Meanwhile, the reference model can assess sample difficulty during data pre-sampling, enabling effective selection of high-gain data to improve training efficiency. Experiments conducted on nine datasets across two domains demonstrate that PVPO achieves State-Of-The-Art (SOTA) performance. Our approach not only demonstrates robust generalization across multiple tasks, but also exhibits scalable performance across models of varying scales.