A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation
A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation
复制标题
DOI：
10.1007/s00466-019-01723-1
复制
发表时间：
2019-03
影响因子：
4.1
通讯作者：
Kun Wang;WaiChing Sun;Q. Du
中科院分区：
文献类型：
--
作者：
Kun Wang;WaiChing Sun;Q. Du
我们引入了多智能体元建模游戏来生成数据、知识和模型，对弹塑性材料的本构响应进行预测。我们引入了图论中的一个新概念，其中建模代理的任务是评估所有重铸为有向多重图的建模选项，并找到将有向图的源（例如应变历史）与目标函数测量的目标（例如应力）联系起来的最佳路径。同时，数据代理的任务是从真实或虚拟实验（例如分子动力学、离散元模拟）生成数据，它与建模代理顺序交互，并使用强化学习来设计新的实验以优化预测能力。因此，这种处理使我们能够模拟理想化的科学合作，通过深度强化学习自动完成决策树搜索中的最佳选择。
We introduce a multi-agent meta-modeling game to generate data, knowledge, and models that make predictions on constitutive responses of elasto-plastic materials. We introduce a new concept from graph theory where a modeler agent is tasked with evaluating all the modeling options recast as a directed multigraph and find the optimal path that links the source of the directed graph (e.g. strain history) to the target (e.g. stress) measured by an objective function. Meanwhile, the data agent, which is tasked with generating data from real or virtual experiments (e.g. molecular dynamics, discrete element simulations), interacts with the modeling agent sequentially and uses reinforcement learning to design new experiments to optimize the prediction capacity. Consequently, this treatment enables us to emulate an idealized scientific collaboration as selections of the optimal choices in a decision tree search done automatically via deep reinforcement learning.