隨著電子商務快速成長與消費者對交付彈性及服務品質要求提升，末端配送逐漸成為物流系統中成本壓力較高且營運限制複雜的環節。在無人自取點配送情境下，路徑規劃不僅需考量配送成本，也必須同時納入取貨點容量限制、初始占用量、節點服務急迫性與配送後容量風險等因素。若配送決策僅以行駛距離最小化為目標，可能忽略部分取貨點因容量不足、接近滿載或服務優先性較高所產生的實際營運風險。 本研究以無人自取點之包裹配送為研究情境，探討單日、靜態需求下之末端路徑規劃問題。系統設定為單一物流中心、單一車輛與單趟配送作業，並假設每日需求、指定取貨點、取貨點最大容量、初始占用量與節點急迫性皆於配送前已知。本研究不考慮配送途中回倉補貨、即時需求新增、包裹重新分派與多趟配送情形，並將問題建構為一個序列決策問題，使車輛能依據當前位置、剩餘車輛容量、取貨點剩餘容量、未配送需求與服務急迫性等資訊，逐步選擇下一個配送節點。本研究採用深度強化學習方法（Deep Reinforcement Learning， DRL），並利用近端策略優化（Proximal Policy Optimization， PPO）作為訓練架構。模型透過狀態設計描述配送系統當前資訊，並透過動作遮罩機制排除不符合容量限制之不可行配送節點，以降低模型產生無效決策的可能性。獎勵函數則同時考量配送完成獎勵、行駛距離懲罰、服務急迫性加權與近滿風險懲罰，使代理人能在配送成本、服務優先性與容量風險之間進行權衡，逐步學習符合問題限制的配送決策策略。 本研究透過電腦模擬實驗，比較所提出之 DRL 方法與傳統啟發式方法在不同問題規模下之表現，並以總行駛距離、配送完成度、容量可行性、服務急迫性與整體路徑品質等指標進行評估。研究結果可用以檢視 DRL 方法應用於無人自取點末端配送路徑規劃問題時的適用性、穩定性與限制，並提供未來在取貨點交付模式下進行配送決策設計與方法改良之參考。;With the rapid growth of e-commerce and the increasing demand for flexible delivery services， last-mile delivery has become one of the most costly and operationally complex parts of logistics systems. In the context of unmanned self-pickup points， routing decisions should consider not only transportation cost， but also pickup point capacity， initial occupancy， service urgency， and capacity risk after delivery. This study investigates a single-day， static-demand last-mile routing problem for parcel delivery to unmanned self-pickup points. The system consists of one depot， one vehicle， and a single delivery trip. Customer demand， assigned pickup points， maximum pickup point capacity， initial occupancy， and service urgency are assumed to be known before delivery. The problem is formulated as a sequential decision-making problem， in which the vehicle selects the next pickup point according to the current system state. To solve this problem， this study adopts a Deep Reinforcement Learning (DRL) approach and uses Proximal Policy Optimization (PPO) as the training framework. The proposed model applies an action masking mechanism to exclude infeasible pickup points that violate capacity constraints. The reward function considers delivery completion， travel distance penalty， urgency-weighted service， and near-capacity risk penalty， enabling the agent to balance routing cost， service priority， and capacity feasibility. Computational experiments are conducted to compare the proposed DRL method with traditional heuristic methods under different problem scales. Performance is evaluated using total travel distance， delivery completion， capacity feasibility， service urgency， and overall route quality. The results provide insights into the applicability， stability， and limitations of DRL for unmanned self-pickup point delivery routing problems.
