# Geodesics, Non-linearities and the Archive of Novelty Search

arXiv: https://arxiv.org/abs/2205.03162 · HTML: https://mlsanity.com/paper/2205.03162/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 6 May 2022.

## Builds on (most cited first, 9 of 9)

- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Quality and Diversity Optimization: A Unifying Modular Framework](https://mlsanity.com/paper/1708.09251/) (2017)
- [From exploration to control: learning object manipulation skills through novelty search and local adaptation](https://mlsanity.com/paper/1901.00811/) (2019)
- [Novelty Search for Deep Reinforcement Learning Policy Network Weights by Action Sequence Edit Metric Distance](https://mlsanity.com/paper/1902.03142/) (2019)
- [Few-shot Quality-Diversity Optimization](https://mlsanity.com/paper/2109.06826/) (2021)
- [Evolution of Swarm Robotics Systems with Novelty Search](https://mlsanity.com/paper/1304.3362/) (2013)
- [Catastrophic forgetting: still a problem for DNNs](https://mlsanity.com/paper/1905.08077/) (2019)
- [BR-NS: an Archive-less Approach to Novelty Search](https://mlsanity.com/paper/2104.03936/) (2021)

## Abstract (arXiv)

The Novelty Search (NS) algorithm was proposed more than a decade ago. However, the mechanisms behind its empirical success are still not well formalized/understood. This short note focuses on the effects of the archive on exploration. Experimental evidence from a few application domains suggests that archive-based NS performs in general better than when Novelty is solely computed with respect to the population. An argument that is often encountered in the literature is that the archive prevents exploration from backtracking or cycling, i.e. from revisiting previously encountered areas in the behavior space. We argue that this is not a complete or accurate explanation as backtracking - beside often being desirable - can actually be enabled by the archive. Through low-dimensional/analytical examples, we show that a key effect of the archive is that it counterbalances the exploration biases that result, among other factors, from the use of inadequate behavior metrics and the non-linearities of the behavior mapping. Our observations seem to hint that attributing a more active role to the archive in sampling can be beneficial.