# Efficient Morphology-Aware Policy Transfer to New Embodiments

arXiv: https://arxiv.org/abs/2508.03660 · HTML: https://mlsanity.com/paper/2508.03660/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 41 of its 52 references that are in the map.
- First posted on arXiv 5 Aug 2025.

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [Contextual Markov Decision Processes](https://mlsanity.com/paper/1502.02259/) (2015)
- [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022)
- [The Benefit of Multitask Representation Learning](https://mlsanity.com/paper/1505.06279/) (2015)
- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?](https://mlsanity.com/paper/1910.03016/) (2019)
- [One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control](https://mlsanity.com/paper/2007.04976/) (2020)
- [Adversarial Reprogramming of Neural Networks](https://mlsanity.com/paper/1806.11146/) (2018)
- [RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation](https://mlsanity.com/paper/2306.11706/) (2023)
- [MetaMorph: Learning Universal Controllers with Transformers](https://mlsanity.com/paper/2203.11931/) (2022)
- [Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources](https://mlsanity.com/paper/2007.08714/) (2020)
- [Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity](https://mlsanity.com/paper/1902.05546/) (2019)
- [My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control](https://mlsanity.com/paper/2010.01856/) (2020)
- [Sample Complexity of Multi-task Reinforcement Learning](https://mlsanity.com/paper/1309.6821/) (2013)
- [Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning](https://mlsanity.com/paper/1801.01432/) (2018)
- [Pro-tuning: Unified Prompt Tuning for Vision Tasks](https://mlsanity.com/paper/2207.14381/) (2022)
- [TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models](https://mlsanity.com/paper/2310.05905/) (2023)
- [Hardware Conditioned Policies for Multi-Robot Transfer Learning](https://mlsanity.com/paper/1811.09864/) (2018)
- [Sharing Knowledge in Multi-Task Deep Reinforcement Learning](https://mlsanity.com/paper/2401.09561/) (2024)
- [One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion](https://mlsanity.com/paper/2409.06366/) (2024)

## Abstract (arXiv)

Morphology-aware policy learning is a means of enhancing policy sample efficiency by aggregating data from multiple agents. These types of policies have previously been shown to help generalize over dynamic, kinematic, and limb configuration variations between agent morphologies. Unfortunately, these policies still have sub-optimal zero-shot performance compared to end-to-end finetuning on morphologies at deployment. This limitation has ramifications in practical applications such as robotics because further data collection to perform end-to-end finetuning can be computationally expensive. In this work, we investigate combining morphology-aware pretraining with parameter efficient finetuning (PEFT) techniques to help reduce the learnable parameters necessary to specialize a morphology-aware policy to a target embodiment. We compare directly tuning sub-sets of model weights, input learnable adapters, and prefix tuning techniques for online finetuning. Our analysis reveals that PEFT techniques in conjunction with policy pre-training generally help reduce the number of samples to necessary to improve a policy compared to training models end-to-end from scratch. We further find that tuning as few as less than 1% of total parameters will improve policy performance compared the zero-shot performance of the base pretrained a policy.