摘要
本文将深度强化学习应用于二维不规则多边形的排样问题中,使用质心到轮廓距离将多边形的形状特征映射到一维向量当中,对于在随机产生的多边形中实现了1%以内的压缩损失.给定多边形零件序列,本文使用多任务的深度强化学习模型对不规则排样件的顺序以及旋转角度进行预测,得到优于标准启发式算法5%–10%的排样效果,并在足够次数的采样后得到优于优化后的遗传算法的结果,能够在最短时间内得到一个较优的初始解,具有一定的泛化能力.
This study applies deep reinforcement learning to the nesting problem of two-dimensional irregular polygons.The shape characteristics of polygons are mapped into one-dimensional vectors according to the distances from the centroid to the contours.For randomly generated polygons,the compression losses are less than 1%.With a given sequence of the polygon items,this study employs a multi-task deep reinforcement learning model to predict the sequence and rotation angle of the irregular nesting items and obtains a nesting result 5%–10%higher than those of the traditional heuristic algorithms.A result better than that of the optimized genetic algorithm is also achieved under a sufficient sampling number.The model can deliver a better initial solution in the shortest time and,therefore,has a generalization ability.
作者
曾焕荣
商慧亮
ZENG Huan-Rong;SHANG Hui-Liang(Academy for Engineering and Technology,Fudan University,Shanghai 200433,China)
出处
《计算机系统应用》
2022年第2期168-175,共8页
Computer Systems & Applications
关键词
排样优化问题
组合优化问题
深度强化学习
编码器-解码器结构
行动家-评论家算法
nesting optimization problem
combinatorial optimization problem
deep reinforcement learning
encoder-decoder structure
actor-critic algorithm