paper-with-me

홈 › Papers

Stabilizing Policy Gradient Methods via Reward Profiling

2025-11-20 · Shihab Ahmed, El Houcine Bergou, Aritra Dutta, Yue Wang arxiv

Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from unreliable reward improvements and slow convergence, due to high variance in gradient estimations. In this paper, we propose a universal reward profiling framework that can be seamlessly integrated with any policy gradient algorithm, where we selectively update the policy based on high-confidence performance estimations. We theoretically justify that our technique will not slow down the convergence of the baseline policy gradient methods, but with high probability, will result in stable and monotonic improvements of their performance. Empirically, on eight continuous-control benchmarks (Box2D and MuJoCo/PyBullet), our profiling yields up to 1.5x faster convergence to near-optimal returns, up to 1.75x reduction in return variance on some setups. Our profiling approach offers a general, theoretically grounded path to more reliable and efficient policy learning in complex environments.

📄 PDF Abstract BibTeX arXiv:2511.16629

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

FLAM: Foundation Model-Based Body Stabilization for Humanoid Locomotion and Manipulation

2025-03-28 · Xianqi Zhang, Hongliang Wei, Wenrui Wang, Xingtao Wang 외

Humanoid robots have attracted significant attention in recent years. Reinforcement Learning (RL) is one of the main ways to control the whole body of humanoid robots. RL enables agents to complete tasks by learning from…

Reinforcement Learning (RL)

GTPO: Stabilizing Group Relative Policy Optimization via Gradient and Entropy Control

2025-08-05 · Marco Simoni, Aleksandar Fontana, Giulio Rossolini, Andrea Saracino 외 arxiv

Group Relative Policy Optimization (GRPO) is a promising policy-based approach for Large Language Model alignment, yet its performance is often limited by training instability and suboptimal convergence. In this paper, w…

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

2025-12-01 · Chujie Zheng, Kai Dang, Bowen Yu, Mingze Li 외 arxiv

This paper proposes a novel formulation for reinforcement learning (RL) with large language models, explaining why and under what conditions the true sequence-level reward can be optimized via a surrogate token-level obj…

Reinforcement Learning

Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process

2024-03-07 · Xiangxin Zhou, Liang Wang, Yichi Zhou

Considering generating samples with high rewards, we focus on optimizing deep neural networks parameterized stochastic differential equations (SDEs), the advanced generative models with high expressiveness, with policy g…

Drug DesignPolicy Gradient Methods

Stabilizing Dynamical Systems via Policy Gradient Methods

2021-10-13 · NeurIPS 2021 12 · Juan C. Perdomo, Jack Umenberger, Max Simchowitz

Stabilizing an unknown control system is one of the most fundamental problems in control systems engineering. In this paper, we provide a simple, model-free algorithm for stabilizing fully observed dynamical systems. Whi…

Policy Gradient Methods