mlsanityData to 7 Oct 2026

Representation Edit Distance as a Measure of Novelty

arXiv 2111.02770 ↗First posted 4 Nov 2021cs.LGcited by 4

Not on the map. Why?

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 5 of its 23 references that are in the map. First posted on arXiv 4 Nov 2021.

Builds on

5 of 23 references.

References · 5

  1. 2020Knowledge Graphscited by 619
  2. 2017Opening the Black Box of Deep Neural Networks via Informationcited by 494
  3. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 413
  4. 2015Deep Learning with Limited Numerical Precisioncited by 368
  5. 2018The Description Length of Deep Learning Modelscited by 71

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3.

4 papers.

  1. 2022NovGrid: A Flexible Grid World for Evaluating Agent Response to Noveltycited by 14
  2. 2023Neuro-Symbolic World Models for Adapting to Open World Noveltycited by 14
  3. 2023Characterizing Novelty in the Military Domaincited by 1
  4. 2023Novelty Accommodating Multi-Agent Planning in High Fidelity Simulated Open Worldcited by 0