Leveraging Human-In-The-Loop Demonstrations in Reinforcement Learning for Digital Twin-Driven Robot Flexibility
We propose a human-in-the-loop online training framework combining a digital twin (DT), reinforcement learning (RL), and human demonstrations.
Key points
- Growing automation makes collaborative robots work in more variable environments, increasing the need for adaptation.
- A dual actor framework integrates imitation learning (IL) without adding a direct imitation loss to the RL actor, so demonstrations can guide adaptation instead of manual reprogramming.
- The proposed framework is demonstrated on the Ufactory Xarm5 collaborative robot, where the robot's end-effector aims to reach the target position while avoiding obstacles.
- The same pattern holds with real human demonstrations collected in virtual reality (VR): with demonstrations that never reach the goal, the dual actor framework reached 83-100% mean deterministic evaluation success, against 0-17% for the two imitation-loss methods.
Sources (1)
- [1]Leveraging Human-In-The-Loop Demonstrations in Reinforcement Learning for Digital Twin-Driven Robot FlexibilityarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 03:26 PM
We propose a human-in-the-loop online training framework combining a digital twin (DT), reinforcement learning (RL), and human demonstrations.
Growing automation makes collaborative robots work in more variable environments, increasing the need for adaptation.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 7, 2026MotherTree: Meta-learning on synthetic data improves decision tree training
- Oct 7, 2026Executing Causal Structure Learning with Linear-Attention Transformers
- Oct 7, 2026Concentration, Not Uncertainty: Why Targeted Synthetic Data Doesn't Help Camouflaged Object Detection
- Oct 6, 2026World Models Dream of Success: Diagnosing and Repairing Failure Insensitivity in Robot World Models
- Oct 6, 2026Learning Transition Kernels of Jump-Diffusion Processes with Conditional Diffusion Models
- Oct 6, 2026Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny Transformers