ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning

• URL: http://arxiv.org/abs/2602.10019v1
• Date: Tue, 10 Feb 2026 17:40:39 GMT
• Title: ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning
• Authors: Qingnan Ren, Shiting Huang, Zhen Fang, Zehui Chen, Lin Chen, Lijun Li, Feng Zhao,
• Abstract summary: We introduce textbfADORA (textbfAdvantage textbfDynamics via textbfOnline textbfRollout textbfAdaptation), a novel framework for policy optimization.
• Score: 32.8666744273094
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning has become a cornerstone technique for developing reasoning models in complex tasks, ranging from mathematical problem-solving to imaginary reasoning. The optimization of these models typically relies on policy gradient methods, whose efficacy hinges on the accurate estimation of an advantage function. However, prevailing methods typically employ static advantage estimation, a practice that leads to inefficient credit assignment by neglecting the dynamic utility of training samples over time. This limitation results in suboptimal policy updates, which in turn manifest as slower convergence rates and increased learning instability, as models fail to adapt to evolving sample utilities effectively. To address this problem, we introduce \textbf{ADORA} (\textbf{A}dvantage \textbf{D}ynamics via \textbf{O}nline \textbf{R}ollout \textbf{A}daptation), a novel framework for policy optimization. ADORA dynamically adjusts the advantage function's weighting by adaptively categorizing training data into temporarily advantageous and disadvantageous samples, based on their evolving utility during online model rollouts. This tailored data differentiation strategy allows ADORA to be seamlessly integrated into existing policy optimization algorithms without significant architectural modifications, enabling the policy to prioritize learning from more informative experiences and thereby achieve more efficient policy updates. Extensive evaluations across diverse model families and varying data scales demonstrate that ADORA is a robust and efficient framework. It significantly enhances long reasoning in both geometric and mathematical tasks, consistently achieving notable performance gains without requiring sensitive hyperparameter tuning.

Related papers

• IPD: Boosting Sequential Policy with Imaginary Planning Distillation in Offline Reinforcement Learning [13.655904209137006]
  We propose textbfImaginary Planning Distillation (IPD), a novel framework that seamlessly incorporates offline planning into data generation, supervised training, and online inference.<n>Our framework first learns a world model equipped with uncertainty measures and a quasi-optimal value function from the offline data.<n>By replacing the conventional, manually-tuned return-to-go with the learned quasi-optimal value function, IPD improves both decision-making stability and performance during inference.
  arXiv  Detail & Related papers  (2026-03-04T17:05:39Z)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• Efficient Inference for Inverse Reinforcement Learning and Dynamic Discrete Choice Models [35.877107409163784]
  Inverse reinforcement learning (IRL) and dynamic discrete choice (DDC) models explain sequential decision-making by recovering reward functions that rationalize observed behavior.<n>We develop a semiparametric framework for debiased inverse reinforcement learning that yields statistically efficient inference for a broad class of reward-dependent functionals.
  arXiv  Detail & Related papers  (2025-12-30T18:41:05Z)
• Reinforcement Learning in Queue-Reactive Models: Application to Optimal Execution [0.35932002706017546]
  We investigate the use of Reinforcement Learning for the optimal execution of meta-orders.<n>The objective is to execute incrementally large orders while minimizing implementation shortfall and market impact.<n>We employ the Queue-Reactive Model to generate realistic and tractable limit order book simulations.
  arXiv  Detail & Related papers  (2025-11-19T09:26:23Z)
• Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning [77.92320830700797]
  Reinforcement Learning has played a central role in enabling reasoning capabilities of Large Language Models.<n>We propose a tractable computational framework that tracks and leverages curvature information during policy updates.<n>The algorithm, Curvature-Aware Policy Optimization (CAPO), identifies samples that contribute to unstable updates and masks them out.
  arXiv  Detail & Related papers  (2025-10-01T12:29:32Z)
• KIPPO: Koopman-Inspired Proximal Policy Optimization [4.46358470535211]
  Reinforcement Learning (RL) has made significant strides in various domains.<n>Policy gradient methods like Proximal Policy (PPO) have gained popularity due to their balance in performance, stability, and computational efficiency.
  arXiv  Detail & Related papers  (2025-05-20T16:25:41Z)
• Online Reinforcement Learning-Based Dynamic Adaptive Evaluation Function for Real-Time Strategy Tasks [5.115170525117103]
  Effective evaluation of real-time strategy tasks requires adaptive mechanisms to cope with dynamic and unpredictable environments.<n>This study proposes a method to improve evaluation functions for real-time responsiveness to battle-field situation changes.
  arXiv  Detail & Related papers  (2025-01-07T14:36:33Z)
• Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning [53.97273491846883]
  We propose DPE: an RL algorithm that blends offline sequence modeling and offline reinforcement learning with Double Policy Estimation. We validate our method in multiple tasks of OpenAI Gym with D4RL benchmarks.
  arXiv  Detail & Related papers  (2023-08-28T20:46:07Z)
• Multiplicative update rules for accelerating deep learning training and increasing robustness [69.90473612073767]
  We propose an optimization framework that fits to a wide range of machine learning algorithms and enables one to apply alternative update rules. We claim that the proposed framework accelerates training, while leading to more robust models in contrast to traditionally used additive update rule.
  arXiv  Detail & Related papers  (2023-07-14T06:44:43Z)
• When to Update Your Model: Constrained Model-based Reinforcement Learning [50.74369835934703]
  We propose a novel and general theoretical scheme for a non-decreasing performance guarantee of model-based RL (MBRL) Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns.
  arXiv  Detail & Related papers  (2022-10-15T17:57:43Z)
• Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models [40.08137765886609]
  We show that our model, called a graph structured surrogate model (GSSM), outperforms state-of-the-art methods in predicting environment dynamics. Our approach is able to obtain high returns, while allowing fast execution during deployment by avoiding test time policy gradient optimization.
  arXiv  Detail & Related papers  (2021-02-16T17:21:55Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)
• Model-Augmented Actor-Critic: Backpropagating through Paths [81.86992776864729]
  Current model-based reinforcement learning approaches use the model simply as a learned black-box simulator. We show how to make more effective use of the model by exploiting its differentiability.
  arXiv  Detail & Related papers  (2020-05-16T19:18:10Z)

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.