# Optimal Neuron Selection: NK Echo State Networks for Reinforcement Learning

arXiv: https://arxiv.org/abs/1505.01887 · HTML: https://mlsanity.com/paper/1505.01887/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2015.

## Built on by (most cited first, 3 of 3)

- [Recursive Least Squares Policy Control with Echo State Network](https://mlsanity.com/paper/2201.04781/) (2022)
- [Quantum Neuron Selection: Finding High Performing Subnetworks With Quantum Algorithms](https://mlsanity.com/paper/2302.05984/) (2023)
- [Towards Scalable Lottery Ticket Networks using Genetic Algorithms](https://mlsanity.com/paper/2508.08877/) (2025)

## Abstract (arXiv)

This paper introduces the NK Echo State Network. The problem of learning in the NK Echo State Network is reduced to the problem of optimizing a special form of a Spin Glass Problem known as an NK Landscape. No weight adjustment is used; all learning is accomplished by spinning up (turning on) or spinning down (turning off) neurons in order to find a combination of neurons that work together to achieve the desired computation. For special types of NK Landscapes, an exact global solution can be obtained in polynomial time using dynamic programming. The NK Echo State Network is applied to a reinforcement learning problem requiring a recurrent network: balancing two poles on a cart given no velocity information. Empirical results shows that the NK Echo State Network learns very rapidly and yields very good generalization.