# Memory Augmented Control Networks

arXiv: https://arxiv.org/abs/1709.05706 · HTML: https://mlsanity.com/paper/1709.05706/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2017.

## Built on by (most cited first, 13 of 13)

- [Coupling Vision and Proprioception for Navigation of Legged Robots](https://mlsanity.com/paper/2112.02094/) (2021)
- [Following High-level Navigation Instructions on a Simulated Quadcopter with Imitation Learning](https://mlsanity.com/paper/1806.00047/) (2018)
- [Differentiable Spatial Planning using Transformers](https://mlsanity.com/paper/2112.01010/) (2021)
- [Embodied AI: From LLMs to World Models](https://mlsanity.com/paper/2509.20021/) (2025)
- [Object Memory Transformer for Object Goal Navigation](https://mlsanity.com/paper/2203.14708/) (2022)
- [Learning Reward Machines: A Study in Partially Observable Reinforcement Learning](https://mlsanity.com/paper/2112.09477/) (2021)
- [Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning](https://mlsanity.com/paper/2101.00186/) (2021)
- [Building spatial world models from sparse transitional episodic memories](https://mlsanity.com/paper/2505.13696/) (2025)
- [Hard Attention Control By Mutual Information Maximization](https://mlsanity.com/paper/2103.06371/) (2021)
- [How memory architecture affects learning in a simple POMDP: the two-hypothesis testing problem](https://mlsanity.com/paper/2106.08849/) (2021)
- [Reward Learning using Structural Motifs in Inverse Reinforcement Learning](https://mlsanity.com/paper/2209.13489/) (2022)
- [Discovering Continuous-Time Memory-Based Symbolic Policies using Genetic Programming](https://mlsanity.com/paper/2406.02765/) (2024)
- [Artifacts as Memory Beyond the Agent Boundary](https://mlsanity.com/paper/2604.08756/) (2026)

## Abstract (arXiv)

Planning problems in partially observable environments cannot be solved directly with convolutional networks and require some form of memory. But, even memory networks with sophisticated addressing schemes are unable to learn intelligent reasoning satisfactorily due to the complexity of simultaneously learning to access memory and plan. To mitigate these challenges we introduce the Memory Augmented Control Network (MACN). The proposed network architecture consists of three main parts. The first part uses convolutions to extract features and the second part uses a neural network-based planning module to pre-plan in the environment. The third part uses a network controller that learns to store those specific instances of past information that are necessary for planning. The performance of the network is evaluated in discrete grid world environments for path planning in the presence of simple and complex obstacles. We show that our network learns to plan and can generalize to new environments.