# Towards a practical measure of interference for reinforcement learning

arXiv: https://arxiv.org/abs/2007.03807 · HTML: https://mlsanity.com/paper/2007.03807/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2020.

## Built on by (most cited first, 6 of 6)

- [Investigating the Properties of Neural Network Representations in Reinforcement Learning](https://mlsanity.com/paper/2203.15955/) (2022)
- [The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models](https://mlsanity.com/paper/2510.02230/) (2025)
- [Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn](https://mlsanity.com/paper/2409.04792/) (2024)
- [Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation](https://mlsanity.com/paper/2109.00525/) (2021)
- [Learning Dynamics and Generalization in Reinforcement Learning](https://mlsanity.com/paper/2206.02126/) (2022)
- [Generalization Through the Lens of Learning Dynamics](https://mlsanity.com/paper/2212.05377/) (2022)

## Abstract (arXiv)

Catastrophic interference is common in many network-based learning systems, and many proposals exist for mitigating it. But, before we overcome interference we must understand it better. In this work, we provide a definition of interference for control in reinforcement learning. We systematically evaluate our new measures, by assessing correlation with several measures of learning performance, including stability, sample efficiency, and online and offline control performance across a variety of learning architectures. Our new interference measure allows us to ask novel scientific questions about commonly used deep learning architectures. In particular we show that target network frequency is a dominating factor for interference, and that updates on the last layer result in significantly higher interference than updates internal to the network. This new measure can be expensive to compute; we conclude with motivation for an efficient proxy measure and empirically demonstrate it is correlated with our definition of interference.