# MeMo: Meaningful, Modular Controllers via Noise Injection

arXiv: https://arxiv.org/abs/2407.01567 · HTML: https://mlsanity.com/paper/2407.01567/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 36 references that are in the map.
- First posted on arXiv 24 May 2024.

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

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [A System for General In-Hand Object Re-Orientation](https://mlsanity.com/paper/2111.03043/) (2021)
- [Robust Learning with Jacobian Regularization](https://mlsanity.com/paper/1908.02729/) (2019)
- [Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer](https://mlsanity.com/paper/1609.07088/) (2016)
- [Stochastic Neural Networks for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1704.03012/) (2017)
- [One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control](https://mlsanity.com/paper/2007.04976/) (2020)
- [Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck](https://mlsanity.com/paper/1910.12911/) (2019)
- [State-Only Imitation Learning for Dexterous Manipulation](https://mlsanity.com/paper/2004.04650/) (2020)
- [MetaMorph: Learning Universal Controllers with Transformers](https://mlsanity.com/paper/2203.11931/) (2022)
- [Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost](https://mlsanity.com/paper/1810.06045/) (2018)
- [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)
- [Top-Down Synthesis for Library Learning](https://mlsanity.com/paper/2211.16605/) (2022)
- [An End-to-End Differentiable Framework for Contact-Aware Robot Design](https://mlsanity.com/paper/2107.07501/) (2021)
- [Graph Inverse Reinforcement Learning from Diverse Videos](https://mlsanity.com/paper/2207.14299/) (2022)
- [Noisy Recurrent Neural Networks](https://mlsanity.com/paper/2102.04877/) (2021)
- [Explicit Regularisation in Gaussian Noise Injections](https://mlsanity.com/paper/2007.07368/) (2020)
- [Hierarchically Decoupled Imitation for Morphological Transfer](https://mlsanity.com/paper/2003.01709/) (2020)
- [babble: Learning Better Abstractions with E-Graphs and Anti-Unification](https://mlsanity.com/paper/2212.04596/) (2022)
- [Learning Modular Robot Control Policies](https://mlsanity.com/paper/2105.10049/) (2021)
- [Solving Compositional Reinforcement Learning Problems via Task Reduction](https://mlsanity.com/paper/2103.07607/) (2021)
- [On the Inherent Regularization Effects of Noise Injection During Training](https://mlsanity.com/paper/2102.07379/) (2021)
- [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)
- [Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing](https://mlsanity.com/paper/2103.01009/) (2021)
- [CLAS: Coordinating Multi-Robot Manipulation with Central Latent Action Spaces](https://mlsanity.com/paper/2211.15824/) (2022)

## Built on by (most cited first, 1 of 1)

- [Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges](https://mlsanity.com/paper/2512.04770/) (2025)

## Abstract (arXiv)

Robots are often built from standardized assemblies, (e.g. arms, legs, or fingers), but each robot must be trained from scratch to control all the actuators of all the parts together. In this paper we demonstrate a new approach that takes a single robot and its controller as input and produces a set of modular controllers for each of these assemblies such that when a new robot is built from the same parts, its control can be quickly learned by reusing the modular controllers. We achieve this with a framework called MeMo which learns (Me)aningful, (Mo)dular controllers. Specifically, we propose a novel modularity objective to learn an appropriate division of labor among the modules. We demonstrate that this objective can be optimized simultaneously with standard behavior cloning loss via noise injection. We benchmark our framework in locomotion and grasping environments on simple to complex robot morphology transfer. We also show that the modules help in task transfer. On both structure and task transfer, MeMo achieves improved training efficiency to graph neural network and Transformer baselines.