# My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control

arXiv: https://arxiv.org/abs/2010.01856 · HTML: https://mlsanity.com/paper/2010.01856/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2020.

## Built on by (most cited first, 30 of 70)

- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Recipe for a General, Powerful, Scalable Graph Transformer](https://mlsanity.com/paper/2205.12454/) (2022)
- [Multi-Game Decision Transformers](https://mlsanity.com/paper/2205.15241/) (2022)
- [RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation](https://mlsanity.com/paper/2306.11706/) (2023)
- [Generalized Decision Transformer for Offline Hindsight Information Matching](https://mlsanity.com/paper/2111.10364/) (2021)
- [MetaMorph: Learning Universal Controllers with Transformers](https://mlsanity.com/paper/2203.11931/) (2022)
- [Can Wikipedia Help Offline Reinforcement Learning?](https://mlsanity.com/paper/2201.12122/) (2022)
- [In Defense of the Unitary Scalarization for Deep Multi-Task Learning](https://mlsanity.com/paper/2201.04122/) (2022)
- [Vitruvion: A Generative Model of Parametric CAD Sketches](https://mlsanity.com/paper/2109.14124/) (2021)
- [A Generalist Neural Algorithmic Learner](https://mlsanity.com/paper/2209.11142/) (2022)
- [A Survey on Transformers in Reinforcement Learning](https://mlsanity.com/paper/2301.03044/) (2023)
- [One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion](https://mlsanity.com/paper/2409.06366/) (2024)
- [Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design](https://mlsanity.com/paper/2110.03659/) (2021)
- [Body Transformer: Leveraging Robot Embodiment for Policy Learning](https://mlsanity.com/paper/2408.06316/) (2024)
- [AnyMorph: Learning Transferable Polices By Inferring Agent Morphology](https://mlsanity.com/paper/2206.12279/) (2022)
- [A Generalist Dynamics Model for Control](https://mlsanity.com/paper/2305.10912/) (2023)
- [Universal Morphology Control via Contextual Modulation](https://mlsanity.com/paper/2302.11070/) (2023)
- [Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning](https://mlsanity.com/paper/2203.13733/) (2022)
- [ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robots](https://mlsanity.com/paper/2310.10486/) (2023)
- [LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfer](https://mlsanity.com/paper/2602.10556/) (2026)
- [Low-Rank Modular Reinforcement Learning via Muscle Synergy](https://mlsanity.com/paper/2210.15479/) (2022)
- [Multi-Agent Policy Transfer via Task Relationship Modeling](https://mlsanity.com/paper/2203.04482/) (2022)
- [REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer](https://mlsanity.com/paper/2202.05244/) (2022)
- [A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation](https://mlsanity.com/paper/2211.14296/) (2022)
- [Symmetry-Aware Robot Design with Structured Subgroups](https://mlsanity.com/paper/2306.00036/) (2023)
- [Transformers in Reinforcement Learning: A Survey](https://mlsanity.com/paper/2307.05979/) (2023)
- [Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization](https://mlsanity.com/paper/2110.04686/) (2021)
- [Subequivariant Graph Reinforcement Learning in 3D Environments](https://mlsanity.com/paper/2305.18951/) (2023)
- [Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control](https://mlsanity.com/paper/2402.06570/) (2024)
- [Entity-based Reinforcement Learning for Autonomous Cyber Defence](https://mlsanity.com/paper/2410.17647/) (2024)

## Abstract (arXiv)

Multitask Reinforcement Learning is a promising way to obtain models with better performance, generalisation, data efficiency, and robustness. Most existing work is limited to compatible settings, where the state and action space dimensions are the same across tasks. Graph Neural Networks (GNN) are one way to address incompatible environments, because they can process graphs of arbitrary size. They also allow practitioners to inject biases encoded in the structure of the input graph. Existing work in graph-based continuous control uses the physical morphology of the agent to construct the input graph, i.e., encoding limb features as node labels and using edges to connect the nodes if their corresponded limbs are physically connected. In this work, we present a series of ablations on existing methods that show that morphological information encoded in the graph does not improve their performance. Motivated by the hypothesis that any benefits GNNs extract from the graph structure are outweighed by difficulties they create for message passing, we also propose Amorpheus, a transformer-based approach. Further results show that, while Amorpheus ignores the morphological information that GNNs encode, it nonetheless substantially outperforms GNN-based methods that use the morphological information to define the message-passing scheme.