OR-Transformer is a deep reinforcement learning framework designed for joint replenishment in supply chain operations with thousands of items. It uses a permutation‑equivariant Transformer architecture and pathwise‑gradient training to handle high‑dimensional observation and action spaces. In tests up to 1,024 items, it outperforms both learning‑based and rolling‑horizon MILP baselines and cuts online decision time by over four million times.
arXiv:2606. 06201v1 Announce Type: new Abstract: Pharmaceutical supply chains (PSCs) struggle with inventory management (IM) due to unpredictable demand patterns and variable lead times associated with restocking.
arXiv:2510. 10057v2 Announce Type: replace Abstract: The three-dimensional bin packing problem (3D-BPP) is widely applied in logistics and warehousing.
arXiv:2608. 02343v1 Announce Type: cross Abstract: Many operational problems are constrained sequential decision processes with large, combinatorial action spaces and interdependent feasibility constraints.
arXiv:2607. 22356v1 Announce Type: new Abstract: In recent years, the growing complexity of last-mile pickup operations has increased the need for fast and accurate decision-making on logistics platforms.
arXiv:2607. 02941v1 Announce Type: new Abstract: Multi-product kitting delivery imposes significant challenges for real-time scheduling in hybrid manufacturing systems that integrate processing and assembly, as dynamic order arrivals simultaneously alter supply dependencies and the set of feasible job-machine assignments.
arXiv:2606. 18820v1 Announce Type: cross Abstract: Sequential decision problems often exhibit an asymmetric evolution of information and decision flexibility: as a decision cycle unfolds, the agent receives richer information while feasible actions expire due to operational cutoffs, commitments, or resource constraints.
The paper introduces proximal residual value functions for two‑timescale decision systems, where a planning layer supplies a continuation‑value function to a real‑time optimizer that allocates resources, with inventory placement as a motivating example. The authors propose an end‑to‑end reinforcement learning method that learns a convex residual added to a strictly convex potential, enabling well‑posed optimization and end‑to‑end differentiation while maintaining an explicit convex objective for real‑time execution. They also provide necessary and sufficient conditions for smooth value functions to produce decisions consistent across planning and execution timescales, and demonstrate a 5.0% reduction in routing and transfer cost in an offline simulation using data from a large e‑commerce retailer.
arXiv:2607. 28488v1 Announce Type: cross Abstract: Can supply-chain AI move beyond isolated decision modules toward unified operational planning?
arXiv:2606. 13682v1 Announce Type: new Abstract: The open shop scheduling problem (OSSP) arises in many industrial and service settings but remains computationally challenging as the number of jobs and machines increases.
arXiv:2607. 16875v1 Announce Type: cross Abstract: We introduce the vehicle routing problem with stochastic demands and outsourcing options (VRP-SDO), in which a logistics service provider partitions customer requests into customers outsourced to a common carrier and customers committed to its fixed fleet.
arXiv:2606. 13604v1 Announce Type: new Abstract: Dispatch in three-sided marketplaces provides a natural setting for reinforcement learning from world feedback: decisions are evaluated by delayed operational outcomes such as delivery speed, courier utilization, and merchant congestion.
The paper introduces a novel end‑to‑end, size‑agnostic graph reinforcement learning framework for the one‑dimensional bin packing problem (1D‑BPP). It models packing as a Markov decision process on an item‑compatibility graph, where a graph neural network actor‑critic policy learns to merge compatible partial bins. Empirical results on the BPPLIB benchmark show that the learned policy reduces the mean optimality gap of a constructive heuristic from 2.66 % to 2.31 %, performs competitively against other learned methods, and outperforms a state‑of‑the‑art learned solver on the hardest benchmark family.