Image de couverture de livre

Posterior Optimization with Clipped Objective for Bridging Efficiency and Stability in Generative Policy Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Yuhui, Li, Haoran, Jiang, Zhennan, Qin, Yuxing, Wan, Yuxuan, Liu, Weiheng, Zhao, Dongbin
Format:	Preprint
Publié:	2026
Sujets:	Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

TeViR: Text-to-Video Reward with Diffusion Models for Efficient Reinforcement Learning
par: Chen, Yuhui, et autres
Publié: (2025)

Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RL
par: Liu, Xin, et autres
Publié: (2026)

Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning
par: Liu, Yuan, et autres
Publié: (2026)

Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization
par: Li, Haoran, et autres
Publié: (2024)

World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation
par: Jiang, Zhennan, et autres
Publié: (2025)

Survey of Vision-Language-Action Models for Embodied Manipulation
par: Li, Haoran, et autres
Publié: (2025)

DiffuDepGrasp: Diffusion-based Depth Noise Modeling Empowers Sim2Real Robotic Grasping
par: Zhou, Yingting, et autres
Publié: (2025)

ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
par: Chen, Yuhui, et autres
Publié: (2025)

FetchBot: Learning Generalizable Object Fetching in Cluttered Scenes via Zero-Shot Sim2Real
par: Liu, Weiheng, et autres
Publié: (2025)

NeuronsGym: A Hybrid Framework and Benchmark for Robot Tasks with Sim2Real Policy Learning
par: Li, Haoran, et autres
Publié: (2023)

WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
par: Jiang, Zhennan, et autres
Publié: (2026)

QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models
par: Li, Yixuan, et autres
Publié: (2025)

CL3R: 3D Reconstruction and Contrastive Learning for Enhanced Robotic Manipulation Representations
par: Cui, Wenbo, et autres
Publié: (2025)

Boosting Continuous Control with Consistency Policy
par: Chen, Yuhui, et autres
Publié: (2023)

InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation
par: Liu, Jiahao, et autres
Publié: (2026)

HDFlow: Hierarchical Diffusion-Flow Planning for Long-horizon Tasks
par: Gireesh, Nandiraju, et autres
Publié: (2026)

Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning
par: Yu, Dongjie, et autres
Publié: (2026)

Advancing Object Goal Navigation Through LLM-enhanced Object Affinities Transfer
par: Lin, Mengying, et autres
Publié: (2024)

NFPO: Stabilized Policy Optimization of Normalizing Flow for Robotic Policy Learning
par: Shi, Diyuan, et autres
Publié: (2026)

$\mathbf{M^3A}$ Policy: Mutable Material Manipulation Augmentation Policy through Photometric Re-rendering
par: Li, Jiayi, et autres
Publié: (2025)

ComSD: Balancing Behavioral Quality and Diversity in Unsupervised Skill Discovery
par: Liu, Xin, et autres
Publié: (2023)

Trajectory Tracking Using Frenet Coordinates with Deep Deterministic Policy Gradient
par: Jiang, Tongzhou, et autres
Publié: (2024)

Learn With Imagination: Safe Set Guided State-wise Constrained Policy Optimization
par: Sun, Yifan, et autres
Publié: (2023)

Conservative Offline Robot Policy Learning via Posterior-Transition Reweighting
par: Zhang, Wanpeng, et autres
Publié: (2026)

FoldNet: Learning Generalizable Closed-Loop Policy for Garment Folding via Keypoint-Driven Asset and Demonstration Synthesis
par: Chen, Yuxing, et autres
Publié: (2025)

Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimization
par: Honari, Homayoun, et autres
Publié: (2024)

Drift-Based Policy Optimization: Native One-Step Policy Learning for Online Robot Control
par: Gao, Yuxuan, et autres
Publié: (2026)

Many-Objective-Optimized Semi-Automated Robotic Disassembly Sequences
par: Kiyokawa, Takuya, et autres
Publié: (2024)

Can Context Bridge the Reality Gap? Sim-to-Real Transfer of Context-Aware Policies
par: Iannotta, Marco, et autres
Publié: (2025)

ParkingWorld: End-to-End Autonomous Parking Reinforcement Learning from Corrective Experience in 3DGS Simulation
par: Yu, Zhengcheng, et autres
Publié: (2026)

X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models
par: Li, Boyu, et autres
Publié: (2026)

Empowering Multi-Robot Cooperation via Sequential World Models
par: Zhao, Zijie, et autres
Publié: (2025)

Domains as Objectives: Domain-Uncertainty-Aware Policy Optimization through Explicit Multi-Domain Convex Coverage Set Learning
par: Ilboudo, Wendyam Eric Lionel, et autres
Publié: (2024)

Learning from Planned Data to Improve Robotic Pick-and-Place Planning Efficiency
par: Qin, Liang, et autres
Publié: (2025)

PolicyFlow: Policy Optimization with Continuous Normalizing Flow in Reinforcement Learning
par: Yang, Shunpeng, et autres
Publié: (2026)

Learning Multi-Modal Trajectory Policies for Data-Efficient Robotic Manipulation
par: Chen, Zijia, et autres
Publié: (2026)

Absolute Policy Optimization
par: Zhao, Weiye, et autres
Publié: (2023)

Hybrid Diffusion Policies with Projective Geometric Algebra for Efficient Robot Manipulation Learning
par: Sun, Xiatao, et autres
Publié: (2025)

Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robot
par: Xin, Yucheng, et autres
Publié: (2026)

State-wise Constrained Policy Optimization
par: Zhao, Weiye, et autres
Publié: (2023)