# Optimizing the Neural Architecture of Reinforcement Learning Agents

arXiv: https://arxiv.org/abs/2011.14632 · HTML: https://mlsanity.com/paper/2011.14632/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

## Built on by (most cited first, 4 of 4)

- [SeqNAS: Neural Architecture Search for Event Sequence Classification](https://mlsanity.com/paper/2401.03246/) (2024)
- [HyperPPO: A scalable method for finding small policies for robotic control](https://mlsanity.com/paper/2309.16663/) (2023)
- [Learning Computational Efficient Bots with Costly Features](https://mlsanity.com/paper/2308.09629/) (2023)
- [An Integrated Approach to Neural Architecture Search for Deep Q-Networks](https://mlsanity.com/paper/2510.19872/) (2025)

## Abstract (arXiv)

Reinforcement learning (RL) enjoyed significant progress over the last years. One of the most important steps forward was the wide application of neural networks. However, architectures of these neural networks are typically constructed manually. In this work, we study recently proposed neural architecture search (NAS) methods for optimizing the architecture of RL agents. We carry out experiments on the Atari benchmark and conclude that modern NAS methods find architectures of RL agents outperforming a manually selected one.