Adaptive Combination of a Genetic Algorithm and Novelty Search for Deep Neuroevolution

Eyal Segal, Moshe Sipper

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Evolutionary Computation (EC) has been shown to be able to quickly train Deep Artificial Neural Networks (DNNs) to solve Reinforcement Learning (RL) problems. While a Genetic Algorithm (GA) is well-suited for exploiting reward functions that are neither deceptive nor sparse, it struggles when the reward function is either of those. To that end, Novelty Search (NS) has been shown to be able to outperform gradient-following optimizers in some cases, while under-performing in others. We propose a new algorithm: Explore-Exploit ?- Adaptive Learner (E2?AL, or EyAL). By preserving a dynamically-sized niche of novelty-seeking agents, the algorithm manages to maintain population diversity, exploiting the reward signal when possible and exploring otherwise. The algorithm combines both the exploitation power of a GA and the exploration power of NS, while maintaining their simplicity and elegance. Our experiments show that EyAL outperforms NS in most scenarios, while being on par with a GA-and in some scenarios it can outperform both. EyAL also allows the substitution of the exploiting component (GA) and the exploring component (NS) with other algorithms, e.g., Evolution Strategy and Surprise Search, thus opening the door for future research.

Original languageEnglish
Title of host publicationIJCCI 2022 - Proceedings of the 14th International Joint Conference on Computational Intelligence
EditorsThomas Back, Bas van Stein, Christian Wagner, Jonathan Garibaldi, H. K. Lam, Marie Cottrell, Faiyaz Doctor, Joaquim Filipe, Kevin Warwick, Janusz Kacprzyk
PublisherScience and Technology Publications, Lda
Number of pages8
ISBN (Electronic)9789897586118
StatePublished - 1 Jan 2022
Event14th International Joint Conference on Computational Intelligence, IJCCI 2022 - Valletta, Malta
Duration: 24 Oct 202226 Oct 2022

Publication series

NameICETE International Conference on E-Business and Telecommunication Networks (International Joint Conference on Computational Intelligence)
ISSN (Print)2184-2825


Conference14th International Joint Conference on Computational Intelligence, IJCCI 2022


  • Evolutionary Computation
  • Genetic Algorithm
  • Novelty Search
  • Reinforcement Learning

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications
  • Computer Science Applications


Dive into the research topics of 'Adaptive Combination of a Genetic Algorithm and Novelty Search for Deep Neuroevolution'. Together they form a unique fingerprint.

Cite this