A typical supply chain consists of suppliers, manufacturers, distributors, and customers, with supply, production, and distribution being the key links. Coordinating and optimizing these stages to reduce waste and shorten delivery times poses a significant challenge. However, most existing research relies on heuristic algorithms and focuses primarily on the production and distribution stages. In complex large-scale scenarios, the computational efficiency and adaptability of heuristic algorithms often fall short. This paper investigates a combined scheduling problem and a heterogeneous vehicle routing problem. Unlike traditional heuristic approaches, we propose a novel deep-reinforcement learning model. Finally, a Multi-Rollout algorithm is employed for collaborative training. Experimental results demonstrate that the proposed algorithm delivers competitive performance compared to heuristic methods while significantly outperforming them in computation time for individual instances.

Deep reinforcement learning (DRL) has been widely applied to address inventory management problems. To tackle the challenges posed by factors such as backlog, multisource replenishment, and demand priority in multi-echelon inventory systems, this paper proposes a value decomposition-based multi-agent reinforcement learning (MARL) framework. The framework utilizes independent DQN networks, embedded with self-attention and GRU modules, to facilitate distributed learning of local action value functions, thus simplifying the complexity of the action space. Additionally, a hybrid network based on the multi-head attention mechanism is constructed to approximate the joint action value function, aiming to optimize the overall system cost. Experiments have been conducted on various types of supply chain networks, and the results demonstrate the effectiveness and scalability of the proposed framework.

lass imbalance and data obsolescence are two major issues in the field of credit scoring, leading to excessive bias and inaccuracies in the classification process of credit scoring models. In order to augment minority class samples and balance time dependencies, this paper proposes a credit scoring model based on Temporal Sample Interaction Convolutional Network (TSICN) to facilitate better credit risk assessment for financial institutions. It relies on the intrinsic features of the minority class samples to synthesize new data, thereby increasing the quantity of the minority class samples. Through inference and synthesis, It greatly mitigates the loss of information from minority class samples. The synthesized minority class samples, blended with the original data, are inputted into the causal convolutional layers and dilated convolutional layers. The information flow and memory updates are regulated through reset gate and update gate, The reset gate determines how to combine past information with the current input, while the update gate determines how to combine the previous hidden state with the current candidate hidden state. Compared to common methods, TSICN can integrate information features from minority class samples into the synthesis data, focusing more on short-term dependencies while reducing the capture of long-term dependencies. Experimental results show that TSICN achieves excellent credit scoring classification performance on real-world datasets. This enables more accurate prediction of applicant credit risk, thus reducing the risk of loan default.