paper-with-me

홈 › Papers

RL2ML: Finite-Rollout Surrogate Objectives from Reinforcement Learning to Maximum Likelihood

2026-05-28 · Yifu Zheng arxiv

Correctness-based Reinforcement Learning with Verifiable Rewards (RLVR) trains language models from binary feedback on sampled outputs, but the objective optimized in expectation and the stochastic update geometry induced by finite rollout groups are often conflated. This paper develops RL2ML, a family of finite-rollout surrogate objectives with a closed-form, exactly unbiased gradient estimator. The family continuously connects standard reinforcement learning, maximum-likelihood-like training, and beyond-maximum-likelihood objectives while preserving estimator-objective alignment under a fixed rollout budget. We introduce the group-level update scale to characterize how a rollout group is reweighted after its empirical success count is observed, revealing a subcritical-supercritical update-scale transition that is hidden by population-level objective notation alone. Building on this distinction, calibrated metric-gain analysis and exact variance decomposition show that the best choice of surrogate objective is determined neither by proximity to maximum likelihood nor by the population-level weight alone. Instead, it depends jointly on the evaluation metric, local sensitivity, and estimator variance. The remaining degree of freedom in the surrogate objective family can therefore be formulated as a one-dimensional optimization problem rather than treated as an unconstrained hyperparameter.

📄 PDF Abstract BibTeX arXiv:2605.30154

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Staleness-Learning Rate Scaling Laws for Asynchronous RLHF

2026-07-01 · Jingwei Song, Haofeng Xu, Jie Xiao, Chengke Bao 외 arxiv

High-throughput RLHF systems often decouple rollout generation from policy optimization, leading to the use of stale rollouts during learner updates. In this work, we study the effect of such staleness in asynchronous GR…

Maximum Likelihood Reinforcement Learning

2026-02-02 · Fahim Tajwar, Guanning Zeng, Yueer Zhou, Yuda Song 외 arxiv

Reinforcement learning (RL) is the method of choice for training models in setups where the objective function can only be evaluated by sampling from the model. Our key observation is that when the feedback is terminal a…

Reinforcement LearningCode Generation

The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling

2026-05-29 · Andre Herz, Matthijs Pals, Daniel Durstewitz, Georgia Koppe arxiv

Dynamical systems reconstruction (DSR) aims to learn surrogate models that capture the dynamics underlying time-series data. Reliably deploying these surrogates requires uncertainty estimates consistent with the learned …

SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling

2025-09-30 · Yixian Zhang, Shu'ang Yu, Tonghe Zhang, Mo Guang 외 arxiv

Training expressive flow-based policies with off-policy reinforcement learning is notoriously unstable due to gradient pathologies in the multi-step action sampling process. We trace this instability to a fundamental con…

Reinforcement LearningContinuous Control

Model-Agnostic Knowledge Guided Correction for Improved Neural Surrogate Rollout

2025-03-13 · Bharat Srikishan, Daniel O'Malley, Mohamed Mehana, Nicholas Lubbers 외

Modeling the evolution of physical systems is critical to many applications in science and engineering. As the evolution of these systems is governed by partial differential equations (PDEs), there are a number of comput…