arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.02741cs.AI
收藏

基于元学习的多目标优化问题深度强化学习

Meta-Learning-Based Deep Reinforcement Learning for Multiobjective Optimization Problems

Sun Yat-sen University(中山大学)

Zizhen Zhang, Zhiyuan Wu, Hang Zhang, Jiahai Wang

摘要:

深度强化学习(DRL)最近在解决复杂的组合优化问题方面取得了成功。当这些问题扩展到多目标问题时,现有的DRL方法很难灵活有效地处理由目标权重分解确定的多个子问题。本文提出了一种简洁的基于元学习的DRL方法。它首先通过元学习训练元模型。元模型通过几个更新步骤进行微调,以导出相应子问题的子模型。然后相应地构建帕累托前沿。与其他基于学习的方法相比,我们的方法可以大大缩短多个子模型的训练时间。由于元模型的快速性和良好的适应性,可以导出更多的子模型,以提高所找到的解决方案的质量和多样性。对多目标旅行商问题和带时间窗的多目标车辆路径问题的计算实验表明,该方法优于大多数基于学习和迭代的方法.

英文摘要:

Deep reinforcement learning (DRL) has recently shown its success in tackling complex combinatorial optimization problems. When these problems are extended to multiobjective ones, it becomes difficult for the existing DRL approaches to flexibly and efficiently deal with multiple subproblems determined by weight decomposition of objectives. This paper proposes a concise meta-learning-based DRL approach. It first trains a meta-model by meta-learning. The meta-model is fine-tuned with a few update steps to derive submodels for the corresponding subproblems. The Pareto front is then built accordingly. Compared with other learning-based methods, our method can greatly shorten the training time of multiple submodels. Due to the rapid and excellent adaptability of the meta-model, more submodels can be derived so as to increase the quality and diversity of the found solutions. The computational experiments on multiobjective traveling salesman problems and multiobjective vehicle routing problem with time windows demonstrate the superiority of our method over most of learning-based and iteration-based approaches.

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。

↑