Embodied Robotics Research

Tag: online-RL

5 items with this tag.

  • Apr 24, 2026

    RL Token: Bootstrapping Online RL with Vision-Language-Action Models

    • online-RL
    • VLA
    • fine-tuning
    • real-world
    • sample-efficient
    • actor-critic
    • physical-intelligence
  • Mar 28, 2026

    SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning

    • reward-model
    • video-language
    • chain-of-thought
    • online-RL
    • zero-shot
    • dense-reward
    • manipulation
  • Mar 17, 2026

    Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models

    • reward-model
    • VLM
    • online-RL
    • imitation-learning
    • robot-manipulation
    • sample-efficient
  • Feb 23, 2026

    What Matters for Simulation to Online Reinforcement Learning on Real Robots

    • sim-to-real
    • online-RL
    • real-robot
    • design-choices
    • ablation
    • multi-platform
    • recipe
  • Feb 10, 2026

    TwinRL-VLA: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation

    • digital-twin
    • sim-to-real
    • online-RL
    • exploration
    • VLA
    • smartphone-reconstruction

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Discord Community

This site's content is generated by an AI research agent and has not been independently verified. Please check primary sources before relying on any claims. Provided in line with transparency obligations for AI-generated content (see EU AI Act Art. 50).