# Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization

arXiv: https://arxiv.org/abs/2304.03995 · HTML: https://mlsanity.com/paper/2304.03995/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 51 references that are in the map.
- First posted on arXiv 8 Apr 2023.

## Builds on (most cited first, 27 of 27)

- [Learning to learn by gradient descent by gradient descent](https://mlsanity.com/paper/1606.04474/) (2016)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation](https://mlsanity.com/paper/2106.13281/) (2021)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Meta-Gradient Reinforcement Learning](https://mlsanity.com/paper/1805.09801/) (2018)
- [Quality and Diversity Optimization: A Unifying Modular Framework](https://mlsanity.com/paper/1708.09251/) (2017)
- [Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning](https://mlsanity.com/paper/2106.02584/) (2021)
- [Discovered Policy Optimisation](https://mlsanity.com/paper/2210.05639/) (2022)
- [Understanding and correcting pathologies in the training of learned optimizers](https://mlsanity.com/paper/1810.10180/) (2018)
- [Towards Learning Universal Hyperparameter Optimizers with Transformers](https://mlsanity.com/paper/2205.13320/) (2022)
- [Discovering Reinforcement Learning Algorithms](https://mlsanity.com/paper/2007.08794/) (2020)
- [HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenML](https://mlsanity.com/paper/2106.06257/) (2021)
- [Automated Reinforcement Learning (AutoRL): A Survey and Open Problems](https://mlsanity.com/paper/2201.03916/) (2022)
- [Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves](https://mlsanity.com/paper/2009.11243/) (2020)
- [VeLO: Training Versatile Learned Optimizers by Scaling Up](https://mlsanity.com/paper/2211.09760/) (2022)
- [Meta-Gradient Reinforcement Learning with an Objective Discovered Online](https://mlsanity.com/paper/2007.08433/) (2020)
- [The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning](https://mlsanity.com/paper/2109.02869/) (2021)
- [Meta Learning Backpropagation And Improving It](https://mlsanity.com/paper/2012.14905/) (2020)
- [Discovering Evolution Strategies via Meta-Black-Box Optimization](https://mlsanity.com/paper/2211.11260/) (2022)
- [evosax: JAX-based Evolution Strategies](https://mlsanity.com/paper/2212.04180/) (2022)
- [EvoJAX: Hardware-Accelerated Neuroevolution](https://mlsanity.com/paper/2202.05008/) (2022)
- [Introducing Symmetries to Black Box Meta Reinforcement Learning](https://mlsanity.com/paper/2109.10781/) (2021)
- [PEGASUS: A Policy Search Method for Large MDPs and POMDPs](https://mlsanity.com/paper/1301.3878/) (2013)
- [Meta-Learning for Black-box Optimization](https://mlsanity.com/paper/1907.06901/) (2019)
- [Meta Learning Black-Box Population-Based Optimizers](https://mlsanity.com/paper/2103.03526/) (2021)
- [Effective Mutation Rate Adaptation through Group Elite Selection](https://mlsanity.com/paper/2204.04817/) (2022)
- [Learning Not to Learn: Nature versus Nurture in Silico](https://mlsanity.com/paper/2010.04466/) (2020)

## Built on by (most cited first, 30 of 33)

- [Discovering Preference Optimization Algorithms with and for Large Language Models](https://mlsanity.com/paper/2406.08414/) (2024)
- [MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning](https://mlsanity.com/paper/2310.08252/) (2023)
- [Toward Automated Algorithm Design: A Survey and Practical Guide to Meta-Black-Box-Optimization](https://mlsanity.com/paper/2411.00625/) (2024)
- [Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning](https://mlsanity.com/paper/2402.02355/) (2024)
- [Position: Leverage Foundational Models for Black-Box Optimization](https://mlsanity.com/paper/2405.03547/) (2024)
- [When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges](https://mlsanity.com/paper/2401.10510/) (2024)
- [Discovering Temporally-Aware Reinforcement Learning Algorithms](https://mlsanity.com/paper/2402.05828/) (2024)
- [Auto-configuring Exploration-Exploitation Tradeoff in Evolutionary Computation via Deep Reinforcement Learning](https://mlsanity.com/paper/2404.08239/) (2024)
- [B2Opt: Learning to Optimize Black-box Optimization with Little Budget](https://mlsanity.com/paper/2304.11787/) (2023)
- [Reinforced In-Context Black-Box Optimization](https://mlsanity.com/paper/2402.17423/) (2024)
- [Pretrained Optimization Model for Zero-Shot Black Box Optimization](https://mlsanity.com/paper/2405.03728/) (2024)
- [Evolution Transformer: In-Context Evolutionary Optimization](https://mlsanity.com/paper/2403.02985/) (2024)
- [MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization](https://mlsanity.com/paper/2505.17745/) (2025)
- [RLEMMO: Evolutionary Multimodal Optimization Assisted By Deep Reinforcement Learning](https://mlsanity.com/paper/2404.08242/) (2024)
- [Surrogate Learning in Meta-Black-Box Optimization: A Preliminary Study](https://mlsanity.com/paper/2503.18060/) (2025)
- [EvoFed: Leveraging Evolutionary Strategies for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2311.07485/) (2023)
- [NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications](https://mlsanity.com/paper/2311.02394/) (2023)
- [Creative Text-to-Audio Generation via Synthesizer Programming](https://mlsanity.com/paper/2406.00294/) (2024)
- [Discovering Minimal Reinforcement Learning Environments](https://mlsanity.com/paper/2406.12589/) (2024)
- [Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability](https://mlsanity.com/paper/2306.00045/) (2023)
- [Discovering Quality-Diversity Algorithms via Meta-Black-Box Optimization](https://mlsanity.com/paper/2502.02190/) (2025)
- [Accelerating Vehicle Routing via AI-Initialized Genetic Algorithms](https://mlsanity.com/paper/2504.06126/) (2025)
- [Task-free Adaptive Meta Black-box Optimization](https://mlsanity.com/paper/2601.21475/) (2026)
- [SONATA: Self-adaptive Evolutionary Framework for Hardware-aware Neural Architecture Search](https://mlsanity.com/paper/2402.13204/) (2024)
- [Learning Evolution via Optimization Knowledge Adaptation](https://mlsanity.com/paper/2501.02200/) (2025)
- [Detect and Act: Automated Dynamic Optimizer through Meta-Black-Box Optimization](https://mlsanity.com/paper/2601.22542/) (2026)
- [Ever Evolving Evaluator (EV3): Towards Flexible and Reliable Meta-Optimization for Knowledge Distillation](https://mlsanity.com/paper/2310.18893/) (2023)
- [Searching Search Spaces: Meta-evolving a Geometric Encoding for Neural Networks](https://mlsanity.com/paper/2403.14019/) (2024)
- [An Offline Meta Black-box Optimization Framework for Adaptive Design of Urban Traffic Light Management Systems](https://mlsanity.com/paper/2408.07327/) (2024)
- [Discovering new robust local search algorithms with neuro-evolution](https://mlsanity.com/paper/2501.04747/) (2025)

## Abstract (arXiv)

Genetic algorithms constitute a family of black-box optimization algorithms, which take inspiration from the principles of biological evolution. While they provide a general-purpose tool for optimization, their particular instantiations can be heuristic and motivated by loose biological intuition. In this work we explore a fundamentally different approach: Given a sufficiently flexible parametrization of the genetic operators, we discover entirely new genetic algorithms in a data-driven fashion. More specifically, we parametrize selection and mutation rate adaptation as cross- and self-attention modules and use Meta-Black-Box-Optimization to evolve their parameters on a set of diverse optimization tasks. The resulting Learned Genetic Algorithm outperforms state-of-the-art adaptive baseline genetic algorithms and generalizes far beyond its meta-training settings. The learned algorithm can be applied to previously unseen optimization problems, search dimensions & evaluation budgets. We conduct extensive analysis of the discovered operators and provide ablation experiments, which highlight the benefits of flexible module parametrization and the ability to transfer (`plug-in') the learned operators to conventional genetic algorithms.