Cover Image

Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RL

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Xin, Li, Yixuan, Chen, Yuhui, Qin, Yuxing, Li, Haoran, Zhao, Dongbin
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization
by: Li, Haoran, et al.
Published: (2024)

Posterior Optimization with Clipped Objective for Bridging Efficiency and Stability in Generative Policy Learning
by: Chen, Yuhui, et al.
Published: (2026)

TeViR: Text-to-Video Reward with Diffusion Models for Efficient Reinforcement Learning
by: Chen, Yuhui, et al.
Published: (2025)

ComSD: Balancing Behavioral Quality and Diversity in Unsupervised Skill Discovery
by: Liu, Xin, et al.
Published: (2023)

Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations
by: Liu, Xin, et al.
Published: (2025)

Boosting Continuous Control with Consistency Policy
by: Chen, Yuhui, et al.
Published: (2023)

Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning
by: Liu, Yuan, et al.
Published: (2026)

FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions
by: Marta, Daniel, et al.
Published: (2025)

XPG-RL: Reinforcement Learning with Explainable Priority Guidance for Efficiency-Boosted Mechanical Search
by: Zhang, Yiting, et al.
Published: (2025)

Efficient Coordination with the System-Level Shared State: An Embodied-AI Native Modular Framework
by: Deng, Yixuan, et al.
Published: (2026)

Survey of Vision-Language-Action Models for Embodied Manipulation
by: Li, Haoran, et al.
Published: (2025)

FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance
by: Kim, Sungha, et al.
Published: (2026)

Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution
by: Huang, Changxin, et al.
Published: (2024)

On-Robot Reinforcement Learning with Goal-Contrastive Rewards
by: Biza, Ondrej, et al.
Published: (2024)

PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations
by: Yuan, Mingqi, et al.
Published: (2025)

QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models
by: Li, Yixuan, et al.
Published: (2025)

ManiBox: Enhancing Embodied Spatial Generalization via Scalable Simulation Data Generations
by: Tan, Hengkai, et al.
Published: (2024)

Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
by: Guo, Yihong, et al.
Published: (2024)

Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
by: Guan, Weifan, et al.
Published: (2025)

Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
by: Yuan, Yifu, et al.
Published: (2025)

ConceptACT: Episode-Level Concepts for Sample-Efficient Robotic Imitation Learning
by: Karalus, Jakob, et al.
Published: (2026)

Advancing Embodied Intelligence in Robotic-Assisted Endovascular Procedures: A Systematic Review of AI Solutions
by: Yao, Tianliang, et al.
Published: (2025)

DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving
by: Yang, Pengxuan, et al.
Published: (2026)

Robotic Control via Embodied Chain-of-Thought Reasoning
by: Zawalski, Michał, et al.
Published: (2024)

TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning
by: Li, Ge, et al.
Published: (2024)

From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models
by: Li, Zhuofan, et al.
Published: (2026)

Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking
by: So, Junhyuk, et al.
Published: (2025)

From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning
by: Sun, Zhanyi, et al.
Published: (2026)

Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking
by: Bagaria, Vaidehi, et al.
Published: (2026)

CaRL: Learning Scalable Planning Policies with Simple Rewards
by: Jaeger, Bernhard, et al.
Published: (2025)

VLP: Vision-Language Preference Learning for Embodied Manipulation
by: Liu, Runze, et al.
Published: (2025)

Ask1: Development and Reinforcement Learning-Based Control of a Custom Quadruped Robot
by: Zhang, Yang, et al.
Published: (2024)

ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
by: Chen, Yuhui, et al.
Published: (2025)

Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning
by: Lee, Sungyoung, et al.
Published: (2026)

Quantum-Inspired Episode Selection for Monte Carlo Reinforcement Learning via QUBO Optimization
by: Salloum, Hadi, et al.
Published: (2026)

SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation
by: Zhang, Junjie, et al.
Published: (2024)

Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation
by: Xie, Quanting, et al.
Published: (2024)

MoRe-ERL: Learning Motion Residuals using Episodic Reinforcement Learning
by: Huang, Xi, et al.
Published: (2025)

KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
by: Zheng, Zihao, et al.
Published: (2026)

Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation
by: Zhang, Zhilong, et al.
Published: (2026)