# Exchangeable Input Representations for Reinforcement Learning

arXiv: https://arxiv.org/abs/2003.09022 · HTML: https://mlsanity.com/paper/2003.09022/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2020.

## Built on by (most cited first, 5 of 5)

- [Entity-based Reinforcement Learning for Autonomous Cyber Defence](https://mlsanity.com/paper/2410.17647/) (2024)
- [Reinforcement Learning for Industrial Control Network Cyber Security Orchestration](https://mlsanity.com/paper/2106.05332/) (2021)
- [Building Better Environments for Autonomous Cyber Defence](https://mlsanity.com/paper/2604.08805/) (2026)
- [Autonomous Attack Mitigation for Industrial Control Systems](https://mlsanity.com/paper/2111.02445/) (2021)
- [Neural Operators for Multi-Task Control and Adaptation](https://mlsanity.com/paper/2604.03449/) (2026)

## Abstract (arXiv)

Poor sample efficiency is a major limitation of deep reinforcement learning in many domains. This work presents an attention-based method to project neural network inputs into an efficient representation space that is invariant under changes to input ordering. We show that our proposed representation results in an input space that is a factor of m! smaller for inputs of m objects. We also show that our method is able to represent inputs over variable numbers of objects. Our experiments demonstrate improvements in sample efficiency for policy gradient methods on a variety of tasks. We show that our representation allows us to solve problems that are otherwise intractable when using na"ive approaches.