# Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms

arXiv: https://arxiv.org/abs/2103.03697 · HTML: https://mlsanity.com/paper/2103.03697/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 48 references that are in the map.
- First posted on arXiv 5 Mar 2021.

## Builds on (most cited first, 30 of 44)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Deep Visual Foresight for Planning Robot Motion](https://mlsanity.com/paper/1610.00696/) (2016)
- [Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning](https://mlsanity.com/paper/1803.11347/) (2018)
- [RoboNet: Large-Scale Multi-Robot Learning](https://mlsanity.com/paper/1910.11215/) (2019)
- [Probabilistic Model-Agnostic Meta-Learning](https://mlsanity.com/paper/1806.02817/) (2018)
- [One-Shot Imitation Learning](https://mlsanity.com/paper/1703.07326/) (2017)
- [One-Shot Visual Imitation Learning via Meta-Learning](https://mlsanity.com/paper/1709.04905/) (2017)
- [Bayesian Model-Agnostic Meta-Learning](https://mlsanity.com/paper/1806.03836/) (2018)
- [Recasting Gradient-Based Meta-Learning as Hierarchical Bayes](https://mlsanity.com/paper/1801.08930/) (2018)
- [Task-Agnostic Meta-Learning for Few-shot Learning](https://mlsanity.com/paper/1805.07722/) (2018)
- [One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning](https://mlsanity.com/paper/1802.01557/) (2018)
- [Meta-Reinforcement Learning of Structured Exploration Strategies](https://mlsanity.com/paper/1802.07245/) (2018)
- [Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer](https://mlsanity.com/paper/1609.07088/) (2016)
- [One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control](https://mlsanity.com/paper/2007.04976/) (2020)
- [Meta-Learning Probabilistic Inference For Prediction](https://mlsanity.com/paper/1805.09921/) (2018)
- [Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments](https://mlsanity.com/paper/1710.03641/) (2017)
- [Task-Embedded Control Networks for Few-Shot Imitation Learning](https://mlsanity.com/paper/1810.03237/) (2018)
- [Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning](https://mlsanity.com/paper/1801.01432/) (2018)
- [Meta Reinforcement Learning for Sim-to-real Domain Adaptation](https://mlsanity.com/paper/1909.12906/) (2019)
- [Meta-Learning Priors for Efficient Online Bayesian Regression](https://mlsanity.com/paper/1807.08912/) (2018)
- [Hardware Conditioned Policies for Multi-Robot Transfer Learning](https://mlsanity.com/paper/1811.09864/) (2018)

## Built on by (most cited first, 22 of 22)

- [MetaMorph: Learning Universal Controllers with Transformers](https://mlsanity.com/paper/2203.11931/) (2022)
- [Humanoid Policy ~ Human Policy](https://mlsanity.com/paper/2503.13441/) (2025)
- [Universal Morphology Control via Contextual Modulation](https://mlsanity.com/paper/2302.11070/) (2023)
- [Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challenges](https://mlsanity.com/paper/2311.18044/) (2023)
- [Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation](https://mlsanity.com/paper/2408.16228/) (2024)
- [Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations](https://mlsanity.com/paper/2511.22697/) (2025)
- [Latent-Variable Advantage-Weighted Policy Optimization for Offline RL](https://mlsanity.com/paper/2203.08949/) (2022)
- [Reimagining an autonomous vehicle](https://mlsanity.com/paper/2108.05805/) (2021)
- [Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization](https://mlsanity.com/paper/2210.10865/) (2022)
- [Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control](https://mlsanity.com/paper/2402.06570/) (2024)
- [Multi-Task Meta Learning: learn how to adapt to unseen tasks](https://mlsanity.com/paper/2210.06989/) (2022)
- [Tool-as-Interface: Learning Robot Policies from Observing Human Tool Use](https://mlsanity.com/paper/2504.04612/) (2025)
- [Sharing to learn and learning to share; Fitting together Meta-Learning, Multi-Task Learning, and Transfer Learning: A meta review](https://mlsanity.com/paper/2111.12146/) (2021)
- [Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning](https://mlsanity.com/paper/2502.02332/) (2025)
- [Skeletal Feature Compensation for Imitation Learning with Embodiment Mismatch](https://mlsanity.com/paper/2104.07810/) (2021)
- [Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control](https://mlsanity.com/paper/2412.12147/) (2024)
- [Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges](https://mlsanity.com/paper/2512.04770/) (2025)
- [Knowledge Diversion for Efficient Morphology Control and Policy Transfer](https://mlsanity.com/paper/2512.09796/) (2025)
- [RL3: Boosting Meta Reinforcement Learning via RL inside RL2](https://mlsanity.com/paper/2306.15909/) (2023)
- [Task-Oriented Edge-Assisted Cross-System Design for Real-Time Human-Robot Interaction in Industrial Metaverse](https://mlsanity.com/paper/2508.20664/) (2025)
- [Meta-Learning for Rapid Adaptation in Reference Tracking of Uncertain Nonlinear Systems](https://mlsanity.com/paper/2605.22513/) (2026)
- [Bridging Body and Brain: Gene-Driven Morphology--Control Co-Design](https://mlsanity.com/paper/2609.31329/) (2026)

## Abstract (arXiv)

Reinforcement learning methods can achieve significant performance but require a large amount of training data collected on the same robotic platform. A policy trained with expensive data is rendered useless after making even a minor change to the robot hardware. In this paper, we address the challenging problem of adapting a policy, trained to perform a task, to a novel robotic hardware platform given only few demonstrations of robot motion trajectories on the target robot. We formulate it as a few-shot meta-learning problem where the goal is to find a meta-model that captures the common structure shared across different robotic platforms such that data-efficient adaptation can be performed. We achieve such adaptation by introducing a learning framework consisting of a probabilistic gradient-based meta-learning algorithm that models the uncertainty arising from the few-shot setting with a low-dimensional latent variable. We experimentally evaluate our framework on a simulated reaching and a real-robot picking task using 400 simulated robots generated by varying the physical parameters of an existing set of robotic platforms. Our results show that the proposed method can successfully adapt a trained policy to different robotic platforms with novel physical parameters and the superiority of our meta-learning algorithm compared to state-of-the-art methods for the introduced few-shot policy adaptation problem.