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