# Representation Edit Distance as a Measure of Novelty

arXiv: https://arxiv.org/abs/2111.02770 · HTML: https://mlsanity.com/paper/2111.02770/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 23 references that are in the map.
- First posted on arXiv 4 Nov 2021.

## Builds on (most cited first, 5 of 5)

- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [Deep Learning with Limited Numerical Precision](https://mlsanity.com/paper/1502.02551/) (2015)
- [The Description Length of Deep Learning Models](https://mlsanity.com/paper/1802.07044/) (2018)

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

- [NovGrid: A Flexible Grid World for Evaluating Agent Response to Novelty](https://mlsanity.com/paper/2203.12117/) (2022)
- [Neuro-Symbolic World Models for Adapting to Open World Novelty](https://mlsanity.com/paper/2301.06294/) (2023)
- [Characterizing Novelty in the Military Domain](https://mlsanity.com/paper/2302.12314/) (2023)
- [Novelty Accommodating Multi-Agent Planning in High Fidelity Simulated Open World](https://mlsanity.com/paper/2306.12654/) (2023)

## Abstract (arXiv)

Adaptation to novelty is viewed as learning to change and augment existing skills to confront unfamiliar situations. In this paper, we propose that the amount of editing of an effective representation (the Representation Edit Distance or RED) used in a set of skill programs in an agent's mental model is a measure of difficulty for adaptation to novelty. The RED is an intuitive approximation to the change in information content in bit strings measured by comparing pre-novelty and post-novelty skill programs. We also present some notional examples of how to use RED for predicting difficulty.