# Leveraging Human-In-The-Loop Demonstrations in Reinforcement Learning for Digital Twin-Driven Robot Flexibility

arXiv: https://arxiv.org/abs/2610.12140 · HTML: https://mlsanity.com/paper/2610.12140/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 18 of its 49 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 18 of 18)

- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Overcoming Exploration in Reinforcement Learning with Demonstrations](https://mlsanity.com/paper/1709.10089/) (2017)
- [Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards](https://mlsanity.com/paper/1707.08817/) (2017)
- [IQ-Learn: Inverse soft-Q Learning for Imitation](https://mlsanity.com/paper/2106.12142/) (2021)
- [Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios](https://mlsanity.com/paper/2212.11419/) (2022)
- [Demonstration-Guided Reinforcement Learning with Learned Skills](https://mlsanity.com/paper/2107.10253/) (2021)
- [How to Leverage Unlabeled Data in Offline Reinforcement Learning](https://mlsanity.com/paper/2202.01741/) (2022)
- [AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scale](https://mlsanity.com/paper/2111.05424/) (2021)
- [Reinforcement Learning on Variable Impedance Controller for High-Precision Robotic Assembly](https://mlsanity.com/paper/1903.01066/) (2019)
- [Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Study](https://mlsanity.com/paper/2103.11512/) (2021)
- [Improved Deep Reinforcement Learning with Expert Demonstrations for Urban Autonomous Driving](https://mlsanity.com/paper/2102.09243/) (2021)
- [Minimizing Human Assistance: Augmenting a Single Demonstration for Deep Reinforcement Learning](https://mlsanity.com/paper/2209.11275/) (2022)
- [A Framework for Learning from Demonstration with Minimal Human Effort](https://mlsanity.com/paper/2306.09211/) (2023)
- [Man, machine and work in a digital twin setup: a case study](https://mlsanity.com/paper/2006.08760/) (2020)

## Abstract (arXiv)

Growing automation makes collaborative robots work in more variable environments, increasing the need for adaptation. We propose a human-in-the-loop online training framework combining a digital twin (DT), reinforcement learning (RL), and human demonstrations. Unlike DTs used mainly to generate synthetic data before task execution, our DT is synchronized with the physical system in real time through camera feeds, allowing the virtual robot to update its observations and policy from real-world feedback. 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 experiments show that the framework can resume training after a change in the physical workspace and that, with a fixed set of non-optimal demonstrations, the dual actor framework achieves a much higher final success rate than two methods that add an imitation loss to the actor. 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.