paper-with-me

홈 › Papers

Learning to Evolve

2019-05-08 · Jan Schuchardt, Vladimir Golkov, Daniel Cremers

Evolution and learning are two of the fundamental mechanisms by which life adapts in order to survive and to transcend limitations. These biological phenomena inspired successful computational methods such as evolutionary algorithms and deep learning. Evolution relies on random mutations and on random genetic recombination. Here we show that learning to evolve, i.e. learning to mutate and recombine better than at random, improves the result of evolution in terms of fitness increase per generation and even in terms of attainable fitness. We use deep reinforcement learning to learn to dynamically adjust the strategy of evolutionary algorithms to varying circumstances. Our methods outperform classical evolutionary algorithms on combinatorial and continuous optimization problems.

📄 PDF Abstract BibTeX arXiv:1905.03389

Code (1)

jan-schuchardt/learning-to-evolve 공식 구현 pytorch

Tasks

Deep Reinforcement LearningEvolutionary Algorithmsreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization

2025-10-15 · Henrique Assumpção, Diego Ferreira, Leandro Campos, Fabricio Murai arxiv

We introduce CodeEvolve, an open-source framework that couples large language models with island-based evolutionary search for end-to-end algorithmic discovery. CodeEvolve integrates inspiration-based crossover, meta-pro…

OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation

2026-06-16 · Guibin Zhang, Xun Xu, Yanwei Yue, Zikun Su 외 arxiv

Memory has become a standard substrate for self-evolving agents, yet retaining experience is not the same as learning how to evolve through it. Existing memory agents can store trajectories, retrieve reflections, or accu…

BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution

2026-05-31 · Yangzhen Wu, Aaron J. Li, Wenjie Ma, Li Cao 외 arxiv

The rapid progress of frontier large language models has led to widespread benchmark saturation, limiting the ability of existing datasets to differentiate model capabilities or provide useful training signal. For instan…

ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search

2026-02-10 · Alexey Kravatskiy, Valentin Khrulkov, Ivan Oseledets arxiv

LLM-guided evolutionary computation, most notably AlphaEvolve, has been remarkably successful in discovering novel mathematical constructions by solving challenging optimization problems. The standard approach is to evol…

MadEvolve: Evolutionary Optimization of Cosmological Algorithms with Large Language Models

2026-02-17 · Tianyi Li, Shihui Zang, Moritz Münchmeyer arxiv

We develop a general framework to discover scientific algorithms and apply it to three problems in computational cosmology. Our code, MadEvolve, is similar to Google's AlphaEvolve, but places a stronger emphasis on free …