# DROID: Minimizing the Reality Gap using Single-Shot Human Demonstration

arXiv: https://arxiv.org/abs/2102.11003 · HTML: https://mlsanity.com/paper/2102.11003/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2021.

## Built on by (most cited first, 11 of 11)

- [Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration](https://mlsanity.com/paper/2105.06411/) (2021)
- [Visual Reinforcement Learning with Self-Supervised 3D Representations](https://mlsanity.com/paper/2210.07241/) (2022)
- [DROPO: Sim-to-Real Transfer with Offline Domain Randomization](https://mlsanity.com/paper/2201.08434/) (2022)
- [Domain Randomization via Entropy Maximization](https://mlsanity.com/paper/2311.01885/) (2023)
- [Robust Visual Sim-to-Real Transfer for Robotic Manipulation](https://mlsanity.com/paper/2307.15320/) (2023)
- [Pay Attention to How You Drive: Safe and Adaptive Model-Based Reinforcement Learning for Off-Road Driving](https://mlsanity.com/paper/2310.08674/) (2023)
- [Online vs. Offline Adaptive Domain Randomization Benchmark](https://mlsanity.com/paper/2206.14661/) (2022)
- [Domain Randomization for Robust, Affordable and Effective Closed-loop Control of Soft Robots](https://mlsanity.com/paper/2303.04136/) (2023)
- [Neural Fidelity Calibration for Informative Sim-to-Real Adaptation](https://mlsanity.com/paper/2504.08604/) (2025)
- [Statistical Guarantees for Offline Domain Randomization](https://mlsanity.com/paper/2506.10133/) (2025)
- [Towards provable probabilistic safety for scalable embodied AI systems](https://mlsanity.com/paper/2506.05171/) (2025)

## Abstract (arXiv)

Reinforcement learning (RL) has demonstrated great success in the past several years. However, most of the scenarios focus on simulated environments. One of the main challenges of transferring the policy learned in a simulated environment to real world, is the discrepancy between the dynamics of the two environments. In prior works, Domain Randomization (DR) has been used to address the reality gap for both robotic locomotion and manipulation tasks. In this paper, we propose Domain Randomization Optimization IDentification (DROID), a novel framework to exploit single-shot human demonstration for identifying the simulator's distribution of dynamics parameters, and apply it to training a policy on a door opening task. Our results show that the proposed framework can identify the difference in dynamics between the simulated and the real worlds, and thus improve policy transfer by optimizing the simulator's randomization ranges. We further illustrate that based on these same identified parameters, our method can generalize the learned policy to different but related tasks.