# Experience Selection Using Dynamics Similarity for Efficient Multi-Source Transfer Learning Between Robots

arXiv: https://arxiv.org/abs/2003.13150 · HTML: https://mlsanity.com/paper/2003.13150/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2020.

## Built on by (most cited first, 7 of 7)

- [Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challenges](https://mlsanity.com/paper/2311.18044/) (2023)
- [Bridging the Model-Reality Gap with Lipschitz Network Adaptation](https://mlsanity.com/paper/2112.03756/) (2021)
- ["Forgetting" in Machine Learning and Beyond: A Survey](https://mlsanity.com/paper/2405.20620/) (2024)
- [Dimensionless Policies based on the Buckingham π Theorem: Is This a Good Way to Generalize Numerical Results?](https://mlsanity.com/paper/2307.15852/) (2023)
- [Residual Feature Integration is Sufficient to Prevent Negative Transfer](https://mlsanity.com/paper/2505.11771/) (2025)
- [Crazyflow: An Accurate, GPU-Accelerated, Differentiable Drone Simulator in JAX](https://mlsanity.com/paper/2606.01478/) (2026)
- [On Assessing the Usefulness of Proxy Domains for Developing and Evaluating Embodied Agents](https://mlsanity.com/paper/2109.14516/) (2021)

## Abstract (arXiv)

In the robotics literature, different knowledge transfer approaches have been proposed to leverage the experience from a source task or robot -- real or virtual -- to accelerate the learning process on a new task or robot. A commonly made but infrequently examined assumption is that incorporating experience from a source task or robot will be beneficial. In practice, inappropriate knowledge transfer can result in negative transfer or unsafe behaviour. In this work, inspired by a system gap metric from robust control theory, the nu-gap, we present a data-efficient algorithm for estimating the similarity between pairs of robot systems. In a multi-source inter-robot transfer learning setup, we show that this similarity metric allows us to predict relative transfer performance and thus informatively select experiences from a source robot before knowledge transfer. We demonstrate our approach with quadrotor experiments, where we transfer an inverse dynamics model from a real or virtual source quadrotor to enhance the tracking performance of a target quadrotor on arbitrary hand-drawn trajectories. We show that selecting experiences based on the proposed similarity metric effectively facilitates the learning of the target quadrotor, improving performance by 62% compared to a poorly selected experience.