基于深度强化学习的办公流程任务分配优化  

Optimization of office process task allocation based on deep reinforcement learning

作　　者：廖晨阳 于劲松[1] 乐祥立 LIAO Chenyang;YU Jinsong;LE Xiangli(School of Automation Science and Electrical Engineering,Beihang University,Beijing 100191,China;Shenyuan Honors College,Beihang University,Beijing 100191,China)

机构地区：[1]北京航空航天大学自动化科学与电气工程学院,北京100191 [2]北京航空航天大学高等理工学院,北京100191

出　　处：《北京航空航天大学学报》2024年第2期487-498,共12页Journal of Beijing University of Aeronautics and Astronautics

基　　金：国家重点研发计划(2018YFB1004100)。

摘　　要：在办公平台中存在异构流程任务大量并行的情况,不仅需要任务执行者具有较强的能力,也对协同调度系统的性能提出了要求。采用强化学习(RL)算法,结合协作配合度、松弛度等定量分析,并基于马尔可夫博弈理论提出多智能体博弈模型,实现以总体流程配合度和最大完工时间为优化目标的优化调度系统,提高了总体执行效率。以真实的业务系统流程作为实验场景,在相同的优化目标下,对比D3QN等3种深度强化学习(DRL)算法和基于蚁群的元启发式算法,验证了所提方法的有效性。In the office platform,we often need to face a large number of parallel heterogeneous process tasks.This not only tests the ability of task executors but also puts forward requirements for the performance of the scheduling system.The multi-agent game model based on Markov game theory is proposed in this paper,which adopts the reinforcement learning(RL)approach along with quantitative analysis of the degree of cooperation and relaxation.This model realizes the optimal scheduling system with the overall process degree and maximum completion time as the optimization objectives and enhances the overall execution efficiency.Finally,to confirm the efficacy of this approach,the meta-heuristic algorithm based on ant colony and the reinforcement learning algorithm based on D3QN and deep reinforcement learning(DRL)are contrasted using the real business system process as the experimental data and the identical optimization targets.

关 键 词：工作流 任务调度 马尔可夫博弈 深度强化学习 协作度 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]