mlsanityData to 14 Oct 2026

Low Rank Factorizations are Indirect Encodings for Deep Neuroevolution

arXiv 2504.03037 ↗First posted 3 Apr 2025cs.NEcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Deep neuroevolution is a highly scalable alternative to reinforcement learning due to its unique ability to encode network updates in a small number of bytes. Recent insights from traditional deep learning indicate high-dimensional models possess intrinsic, low-rank structure. In this work, we introduce low-rank, factorized neuroevolution: an indirect encoding through which we can search a small space of low-rank factors that enforce underlying structure across a network's weights. We compare our approach with non-factorized networks of similar and smaller size to understand how much performance can be attributed to the smaller search space. We evaluate our method on a language modeling task using transformers, as well as continuous and discrete vision-based reinforcement learning tasks. Our study shows that low-rank, factorized neuroevolution outperforms or is competitive with non-factorized neuroevolution, performing notably well on language modeling. Our results also suggest deleterious factorized mutations have a stronger negative impact on performance than deleterious non-factorized mutations, which significantly reduces the runtime on environments with early termination for bad performers. More broadly, these results show how we can use insights from backpropgation-based methods to enhance neuroevolution

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 12 of its 34 references that are in the map. First posted on arXiv 3 Apr 2025.

Builds on

12 of 34 references.

References · 12

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  4. 2024DoRA: Weight-Decomposed Low-Rank Adaptationcited by 758
  5. 2020Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuningcited by 671
  6. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 574
  7. 2023TinyStories: How Small Can Language Models Be and Still Speak Coherent English?cited by 449
  8. 2020Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsificationcited by 53
  9. 2020Neuroevolution of Self-Interpretable Agentscited by 49
  10. 2019Deep Neuroevolution of Recurrent and Discrete World Modelscited by 23
  11. 2017Safe Mutations for Deep and Recurrent Neural Networks through Output Gradientscited by 15
  12. 2021A coevolutionary approach to deep multi-agent reinforcement learningcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
  2. 2026EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling
  3. 2026The Low-Rank Structure of VLA Reinforcement Learning
  4. 2024EvoMerge: Neuroevolution for Large Language Models
  5. 2023Generative Adversarial Neuroevolution for Control Behaviour Imitation
  6. 2025Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models
  7. 2025Dynamic Rank Reinforcement Learning for Adaptive Low-Rank Multi-Head Self Attention in Large Language Models
  8. 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision