paper-with-me

Papers

Extending Group Relative Policy Optimization to Continuous Control: A Theoretical Framework for Robotic Reinforcement Learning

2025-07-25 · Rajat Khanda, Mohammad Baqar, Sambuddha Chakrabarti, Satyasaran Changdar arxiv

Group Relative Policy Optimization (GRPO) has shown promise in discrete action spaces by eliminating value function dependencies through group-based advantage estimation. However, its application to continuous control remains unexplored, limiting its utility in robotics where continuous actions are essential. This paper presents a theoretical framework extending GRPO to continuous control environments, addressing challenges in high-dimensional action spaces, sparse rewards, and temporal dynamics. Our approach introduces trajectory-based policy clustering, state-aware advantage estimation, and regularized policy updates designed for robotic applications. We provide theoretical analysis of convergence properties and computational complexity, establishing a foundation for future empirical validation in robotic systems including locomotion and manipulation tasks.

📄 PDF Abstract BibTeX arXiv:2507.19555

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningContinuous Control

Similar Papers 제목 키워드 기반

M$^{2}$GRPO: Mamba-based Multi-Agent Group Relative Policy Optimization for Biomimetic Underwater Robots Pursuit

2026-04-21 · Yukai Feng, Zhiheng Wu, Zhengxing Wu, Junwen Gu 외 arxiv

Traditional policy learning methods in cooperative pursuit face fundamental challenges in biomimetic underwater robots, where long-horizon decision making, partial observability, and inter-robot coordination require both…

Decision Making

MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization

2026-01-12 · Yang Zhao, Hepeng Wang, Xiao Ding, Yangou Ouyang 외 arxiv

Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), yet its efficacy is primarily confined to domains with verifiable ground truths. Extending GRPO to…

Group Relative Policy Optimization for Image Captioning

2025-03-03 · Xu Liang

Image captioning tasks usually use two-stage training to complete model optimization. The first stage uses cross-entropy as the loss function for optimization, and the second stage uses self-critical sequence training (S…

DiversityImage CaptioningModel Optimization

Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning

2025-10-22 · Xichen Zhang, Sitong Wu, Yinghao Zhu, Haoru Tan 외 arxiv

Reinforcement learning from verifiable rewards has emerged as a powerful technique for enhancing the complex reasoning abilities of Large Language Models (LLMs). However, these methods are fundamentally constrained by th…

Reinforcement Learning

Learning Without Critics? Revisiting GRPO in Classical Reinforcement Learning Environments

2025-11-05 · Bryan L. M. de Oliveira, Felipe V. Frujeri, Marcos P. C. M. Queiroz, Luana G. B. Martins 외 arxiv

Group Relative Policy Optimization (GRPO) has emerged as a scalable alternative to Proximal Policy Optimization (PPO) by eliminating the learned critic and instead estimating advantages through group-relative comparisons…

Reinforcement LearningContinuous Control