Image de couverture de livre

Comparative Analysis and Parametric Tuning of PPO, GRPO, and DAPO for LLM Reasoning Enhancement

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Lian, Yongsheng
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

GRPO-$λ$: Credit Assignment improves LLM Reasoning
par: Parthasarathi, Prasanna, et autres
Publié: (2025)

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
par: Ramesh, Shyam Sundhar, et autres
Publié: (2026)

Uncalibrated Reasoning: GRPO Induces Overconfidence for Stochastic Outcomes
par: Bereket, Michael, et autres
Publié: (2025)

Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
par: Zhang, Xichen, et autres
Publié: (2025)

GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO
par: Dipta, Shubhashis Roy, et autres
Publié: (2026)

Segmental Advantage Estimation: Enhancing PPO for Long-Context LLM Training
par: Gong, Xue, et autres
Publié: (2026)

S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models
par: Dai, Muzhi, et autres
Publié: (2025)

AMIR-GRPO: Inducing Implicit Preference Signals into GRPO
par: Yari, Amir Hossein, et autres
Publié: (2026)

ExGRPO: Learning to Reason from Experience
par: Zhan, Runzhe, et autres
Publié: (2025)

7B Fully Open Source Moxin-LLM/VLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement
par: Zhao, Pu, et autres
Publié: (2024)

From Reasoning to Code: GRPO Optimization for Underrepresented Languages
par: Pennino, Federico, et autres
Publié: (2025)

What is the Alignment Objective of GRPO?
par: Vojnovic, Milan, et autres
Publié: (2025)

Mode-Dependent Rectification for Stable PPO Training
par: Mohamad, Mohamad, et autres
Publié: (2026)

GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning
par: Wang, Jingyi, et autres
Publié: (2026)

Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
par: Chen, Peter, et autres
Publié: (2025)

GRPO is Secretly a Process Reward Model
par: Sullivan, Michael, et autres
Publié: (2025)

Learning to Tune Pure Pursuit in Autonomous Racing: Joint Lookahead and Steering-Gain Control with PPO
par: Elgouhary, Mohamed, et autres
Publié: (2026)

Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents
par: Zhu, Mingkang, et autres
Publié: (2025)

SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization
par: Zheng, Zhi, et autres
Publié: (2025)

CIM-PPO:Proximal Policy Optimization with Liu-Correntropy Induced Metric
par: Guo, Yunxiao, et autres
Publié: (2021)

PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping
par: Huang, Nai-Chieh, et autres
Publié: (2023)

ExO-PPO: an Extended Off-policy Proximal Policy Optimization Algorithm
par: Wang, Hanyong, et autres
Publié: (2026)

Representation over Routing: Diagnosing Temporal Routing Pathologies in Multi-Timescale PPO
par: Sun, Jing
Publié: (2026)

Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients
par: Mansouri, Omar El, et autres
Publié: (2025)

A Unified Framework for Rethinking Policy Divergence Measures in GRPO
par: Wu, Qingyuan, et autres
Publié: (2026)

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
par: Ren, Yiming, et autres
Publié: (2026)

An Approximate Ascent Approach To Prove Convergence of PPO
par: Doering, Leif, et autres
Publié: (2026)

IB-GRPO: Aligning LLM-based Learning Path Recommendation with Educational Objectives via Indicator-Based Group Relative Policy Optimization
par: Wang, Shuai, et autres
Publié: (2026)

When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift
par: Vogt-Lowell, Kevin, et autres
Publié: (2026)

When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic
par: Fernández-Hernández, Alberto, et autres
Publié: (2026)

CoRPO: Adding a Correctness Bias to GRPO Improves Generalization
par: Garg, Anisha, et autres
Publié: (2025)

Prefix Grouper: Efficient GRPO Training through Shared-Prefix Forward
par: Liu, Zikang, et autres
Publié: (2025)

TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing
par: Li, Yuanpeng, et autres
Publié: (2026)

FPBoost: Fully Parametric Gradient Boosting for Survival Analysis
par: Archetti, Alberto, et autres
Publié: (2024)

BinaryPPO: Efficient Policy Optimization for Binary Classification
par: Pandey, Punya Syon, et autres
Publié: (2026)

DPO Meets PPO: Reinforced Token Optimization for RLHF
par: Zhong, Han, et autres
Publié: (2024)

A Robust PPO-optimized Tabular Transformer Framework for Intrusion Detection in Industrial IoT Systems
par: She, Yuanya
Publié: (2025)

OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference
par: Wang, Zhuoyuan, et autres
Publié: (2026)

Alignment Dynamics in LLM Fine-Tuning
par: Huang, Yuhan, et autres
Publié: (2026)

Discovering Hidden Algebraic Structures via Transformers with Rank-Aware Beam GRPO
par: Lee, Jaeha, et autres
Publié: (2025)