基于深度强化学习的随机资源受限多项目动态调度策略

目前对于随机工期的分布式资源受限多项目调度问题（SDRCMPSP）的研究较少且大多数为静态调度方案，无法针对环境的变化实时地对策略进行调整优化，及时响应频繁发生的动态因素。为此建立了最小化总拖期成本为目标的随机资源受限多项目动态调度DRL模型，设计了相应的智能体交互环境，采用强化学习中的DDDQN算法对模型进行求解。实验首先对算法的超参数进行灵敏度分析，其次将最优组合在活动工期可变和到达时间不确定两种不同条件下对模型进行训练及测试，结果表明深度强化学习算法能够得到优于任意单一规则的调度结果，有效减少随机资源受限多项目期望总拖期成本，多项目调度决策优化提供良好的依据。

Stochastic resource-constrained multi-project dynamic scheduling strategy based on deep reinforcement learning

There are few studies on the problem of stochastic resource-constrained distributed multi-project scheduling(SDRCMPSP) and most of them are static scheduling schemes, which cannot adjust and optimize the strategy in real time according to changes in the environment and respond to frequent dynamic factors in a timely manner. Therefore, this paper established a stochastic resource-constrained multi-project dynamic scheduling DRL model with the goal of minimizing the total drag cost, designed the corresponding agent interaction environment, and used the DDDQN algorithm in reinforcement learning to solve the model. The experiment first analyzes the hyperparameters of the algorithm, and then trained and tested the model under two different conditions of variable activity duration and uncertain arrival time, and the results show that the deep reinforcement learning algorithm can obtain scheduling results that are better than any single rule, effectively reduce the total drag-off cost of random resources limited multi-project expectations, and provide a good basis for multi-project scheduling decision optimization.