arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.03389cs.NEcs.AIcs.CVcs.LGstat.ML
收藏

学习进化

Learning to Evolve

Technical University of Munich(慕尼黑工业大学)

Jan Schuchardt, Vladimir Golkov, Daniel Cremers

摘要:

进化和学习是生命为了生存和超越局限而适应的两个基本机制。这些生物现象激发了进化算法和深度学习等成功的计算方法。进化依赖于随机突变和随机基因重组。在这里,我们表明,学习进化,即学习变异和重组比随机更好,改善了进化的结果,在每一代的适应度增加,甚至在可达到的适应度。我们使用深度强化学习来学习动态调整进化算法的策略以适应不同的环境。我们的方法优于经典的组合和连续优化问题的进化算法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑