Willem van Jaarsveld

Riccardo Lo Bianco, Remco Dijkman, Wim Nuijten et al.

Dynamic task assignment involves assigning arriving tasks to a limited number of resources in order to minimize the overall cost of the assignments. To achieve optimal task assignment, it is necessary to model the assignment problem first. While there exist separate formalisms, specifically Markov Decision Processes and (Colored) Petri Nets, to model, execute, and solve different aspects of the problem, there is no integrated modeling technique. To address this gap, this paper proposes Action-Evolution Petri Nets (A-E PN) as a framework for modeling and solving dynamic task assignment problems. A-E PN provides a unified modeling technique that can represent all elements of dynamic task assignment problems. Moreover, A-E PN models are executable, which means they can be used to learn close-to-optimal assignment policies through Reinforcement Learning (RL) without additional modeling effort. To evaluate the framework, we define a taxonomy of archetypical assignment problems. We show for three cases that A-E PN can be used to learn close-to-optimal assignment policies. Our results suggest that A-E PN can be used to model and solve a broad range of dynamic task assignment problems.

Riccardo Lo Bianco, Remco Dijkman, Wim Nuijten et al.

Dynamic task assignment concerns the optimal assignment of resources to tasks in a business process. Recently, Deep Reinforcement Learning (DRL) has been proposed as the state of the art for solving assignment problems. DRL methods usually employ a neural network (NN) as an approximator for the policy function, which ingests the state of the process and outputs a valuation of the possible assignments. However, representing the state and the possible assignments so that they can serve as inputs and outputs for a policy NN remains an open challenge, especially when tasks or resources have features with an infinite number of possible values. To solve this problem, this paper proposes a method for representing and solving assignment problems with infinite state and action spaces. In doing so, it provides three contributions: (I) A graph-based feature representation of assignment problems, which we call assignment graph; (II) A mapping from marked Colored Petri Nets to assignment graphs; (III) An adaptation of the Proximal Policy Optimization algorithm that can learn to solve assignment problems represented through assignment graphs. To evaluate the proposed representation method, we model three archetypal assignment problems ranging from finite to infinite state and action space dimensionalities. The experiments show that the method is suitable for representing and learning close-to-optimal task assignment policies regardless of the state and action space dimensionalities.

Riccardo Lo Bianco, Willem van Jaarsveld, Jeroen Middelhuis et al.

The Dynamic Task Assignment Problem (DTAP) concerns matching resources to tasks in real time while minimizing some objectives, like resource costs or task cycle time. In this work, we consider a DTAP variant where every task is a case composed of a stochastic sequence of activities. The DTAP, in this case, involves the decision of which employee to assign to which activity to process requests as quickly as possible. In recent years, Deep Reinforcement Learning (DRL) has emerged as a promising tool for tackling this DTAP variant, but most research is limited to solving small-scale, synthetic problems, neglecting the challenges posed by real-world use cases. To bridge this gap, this work proposes a DRL-based Decision Support System (DSS) for real-world scale DTAPS. To this end, we introduce a DRL agent with two novel elements: a graph structure for observations and actions that can effectively represent any DTAP and a reward function that is provably equivalent to the objective of minimizing the average cycle time of tasks. The combination of these two novelties allows the agent to learn effective and generalizable assignment policies for real-world scale DTAPs. The proposed DSS is evaluated on five DTAP instances whose parameters are extracted from real-world logs through process mining. The experimental evaluation shows how the proposed DRL agent matches or outperforms the best baseline in all DTAP instances and generalizes on different time horizons and across instances.

Francesco Stranieri, Chaaben Kouki, Willem van Jaarsveld et al.

We study inventory control policies for pharmaceutical supply chains, addressing challenges such as perishability, yield uncertainty, and non-stationary demand, combined with batching constraints, lead times, and lost sales. Collaborating with Bristol-Myers Squibb (BMS), we develop a realistic case study incorporating these factors and benchmark three policies--order-up-to (OUT), projected inventory level (PIL), and deep reinforcement learning (DRL) using the proximal policy optimization (PPO) algorithm--against a BMS baseline based on human expertise. We derive and validate bounds-based procedures for optimizing OUT and PIL policy parameters and propose a methodology for estimating projected inventory levels, which are also integrated into the DRL policy with demand forecasts to improve decision-making under non-stationarity. Compared to a human-driven policy, which avoids lost sales through higher holding costs, all three implemented policies achieve lower average costs but exhibit greater cost variability. While PIL demonstrates robust and consistent performance, OUT struggles under high lost sales costs, and PPO excels in complex and variable scenarios but requires significant computational effort. The findings suggest that while DRL shows potential, it does not outperform classical policies in all numerical experiments, highlighting 1) the need to integrate diverse policies to manage pharmaceutical challenges effectively, based on the current state-of-the-art, and 2) that practical problems in this domain seem to lack a single policy class that yields universally acceptable performance.

Tarkan Temizöz, Christina Imdahl, Remco Dijkman et al.

Deploying deep reinforcement learning (DRL) in real-world inventory management presents challenges, including dynamic environments and uncertain problem parameters, e.g. demand and lead time distributions. These challenges highlight a research gap, suggesting a need for a unifying framework to model and solve sequential decision-making under parameter uncertainty. We address this by exploring an underexplored area of DRL for inventory management: training generally capable agents (GCAs) under zero-shot generalization (ZSG). Here, GCAs are advanced DRL policies designed to handle a broad range of sampled problem instances with diverse inventory challenges. ZSG refers to the ability to successfully apply learned policies to unseen instances with unknown parameters without retraining. We propose a unifying Super-Markov Decision Process formulation and the Train, then Estimate and Decide (TED) framework to train and deploy a GCA tailored to inventory management applications. The TED framework consists of three phases: training a GCA on varied problem instances, continuously estimating problem parameters during deployment, and making decisions based on these estimates. Applied to periodic review inventory problems with lost sales, cyclic demand patterns, and stochastic lead times, our trained agent, the Generally Capable Lost Sales Network (GC-LSN) consistently outperforms well-known traditional policies when problem parameters are known. Moreover, under conditions where demand and/or lead time distributions are initially unknown and must be estimated, we benchmark against online learning methods that provide worst-case performance guarantees. Our GC-LSN policy, paired with the Kaplan-Meier estimator, is demonstrated to complement these methods by providing superior empirical performance.

Xiao Mao, Albert H. Schrotenboer, Guohua Wu et al.

Problem definition: For original equipment manufacturers (OEMs), high-tech maintenance is a strategic component in after-sales services, involving close coordination between customers and service engineers. Each customer suggests several time slots for their maintenance task, from which the OEM must select one. This decision needs to be made promptly to support customers' planning. At the end of each day, routes for service engineers are planned to fulfill the tasks scheduled for the following day. We study this hierarchical and sequential decision-making problem-the Dynamic Time Slot Assignment Problem with Commitments and Customer Preferences (DTSAP-CCP)-in this paper. Methodology/results: Two distinct approaches are proposed: 1) an attention-based deep reinforcement learning with rollout execution (ADRL-RE) and 2) a scenario-based planning approach (SBP). The ADRL-RE combines a well-trained attention-based neural network with a rollout framework for online trajectory simulation. To support the training, we develop a neural heuristic solver that provides rapid route planning solutions, enabling efficient learning in complex combinatorial settings. The SBP approach samples several scenarios to guide the time slot assignment. Numerical experiments demonstrate the superiority of ADRL-RE and the stability of SBP compared to both rule-based and rollout-based approaches. Furthermore, the strong practicality of ADRL-RE is verified in a case study of after-sales service for large medical equipment. Implications: This study provides OEMs with practical decision-support tools for dynamic maintenance scheduling, balancing customer preferences and operational efficiency. In particular, our ADRL-RE shows strong real-world potential, supporting timely and customer-aligned maintenance scheduling.

Riccardo Lo Bianco, Willem van Jaarsveld, Remco Dijkman

Process management systems support key decisions about the way work is allocated in organizations. This includes decisions on which task to perform next, when to execute the task, and who to assign the task to. Suitable software tools are required to support these decisions in a way that is optimal for the organization. This paper presents a software library, called GymPN, that supports optimal decision-making in business processes using Deep Reinforcement Learning. GymPN builds on previous work that supports task assignment in business processes, introducing two key novelties: support for partial process observability and the ability to model multiple decisions in a business process. These novel elements address fundamental limitations of previous work and thus enable the representation of more realistic process decisions. We evaluate the library on eight typical business process decision-making problem patterns, showing that GymPN allows for easy modeling of the desired problems, as well as learning optimal decision policies.

Yueyi Li, Mehrdad Mohammadi, Xiaodong Zhang et al.

Mixed service mode docks enhance efficiency by flexibly handling both loading and unloading trucks in warehouses. However, existing research often predetermines the number and location of these docks prior to planning truck assignment and sequencing. This paper proposes a new model integrating dock mode decision, truck assignment, and scheduling, thus enabling adaptive dock mode arrangements. Specifically, we introduce a Q-learning-based adaptive large neighborhood search (Q-ALNS) algorithm to address the integrated problem. The algorithm adjusts dock modes via perturbation operators, while truck assignment and scheduling are solved using destroy and repair local search operators. Q-learning adaptively selects these operators based on their performance history and future gains, employing the epsilon-greedy strategy. Extensive experimental results and statistical analysis indicate that the Q-ALNS benefits from efficient operator combinations and its adaptive mechanism, consistently outperforming benchmark algorithms in terms of optimality gap and Pareto front discovery. In comparison to the predetermined service mode, our adaptive strategy results in lower average tardiness and makespan, highlighting its superior adaptability to varying demands.

Paulo da Costa, Peter Verleijsdonk, Simon Voorberg et al.

Downtime of industrial assets such as wind turbines and medical imaging devices comes at a sharp cost. To avoid such downtime costs, companies seek to initiate maintenance just before failure. Unfortunately, this is challenging for the following two reasons: On the one hand, because asset failures are notoriously difficult to predict, even in the presence of real-time monitoring devices which signal early degradation. On the other hand, because the available resources to serve a network of geographically dispersed assets are typically limited. In this paper, we propose a novel dynamic traveling maintainer problem with alerts model that incorporates these two challenges and we provide three solution approaches on how to dispatch the limited resources. Namely, we propose: (i) Greedy heuristic approaches that rank assets on urgency, proximity and economic risk; (ii) A novel traveling maintainer heuristic approach that optimizes short-term costs; and (iii) A deep reinforcement learning (DRL) approach that optimizes long-term costs. Each approach has different requirements concerning the available alert information. Experiments with small asset networks show that all methods can approximate the optimal policy when given access to complete condition information. For larger networks, the proposed methods yield competitive policies, with DRL consistently achieving the lowest costs.

Tarkan Temizöz, Christina Imdahl, Remco Dijkman et al.

The application of Deep Reinforcement Learning (DRL) to inventory management is an emerging field. However, traditional DRL algorithms, originally developed for diverse domains such as game-playing and robotics, may not be well-suited for the specific challenges posed by inventory management. Consequently, these algorithms often fail to outperform established heuristics; for instance, no existing DRL approach consistently surpasses the capped base-stock policy in lost sales inventory control. This highlights a critical gap in the practical application of DRL to inventory management: the highly stochastic nature of inventory problems requires tailored solutions. In response, we propose Deep Controlled Learning (DCL), a new DRL algorithm designed for highly stochastic problems. DCL is based on approximate policy iteration and incorporates an efficient simulation mechanism, combining Sequential Halving with Common Random Numbers. Our numerical studies demonstrate that DCL consistently outperforms state-of-the-art heuristics and DRL algorithms across various inventory settings, including lost sales, perishable inventory systems, and inventory systems with random lead times. DCL achieves lower average costs in all test cases while maintaining an optimality gap of no more than 0.2\%. Remarkably, this performance is achieved using the same hyperparameter set across all experiments, underscoring the robustness and generalizability of our approach. These findings contribute to the ongoing exploration of tailored DRL algorithms for inventory management, providing a foundation for further research and practical application in this area.