Reinforcement Learning for Solving Stochastic Vehicle Routing Problem with Time Windows

This paper introduces a reinforcement learning approach to optimize the Stochastic Vehicle Routing Problem with Time Windows (SVRP), focusing on reducing travel costs in goods delivery. We develop a novel SVRP formulation that accounts for uncertain travel costs and demands, alongside specific customer time windows. An attention-based neural network trained through reinforcement learning is employed to minimize routing costs. Our approach addresses a gap in SVRP research, which traditionally relies on heuristic methods, by leveraging machine learning. The model outperforms the Ant-Colony Optimization algorithm, achieving a 1.73% reduction in travel costs. It uniquely integrates external information, demonstrating robustness in diverse environments, making it a valuable benchmark for future SVRP studies and industry application.

Reinforcement Learning for Solving Stochastic Vehicle Routing Problem

This study addresses a gap in the utilization of Reinforcement Learning (RL) and Machine Learning (ML) techniques in solving the Stochastic Vehicle Routing Problem (SVRP) that involves the challenging task of optimizing vehicle routes under uncertain conditions. We propose a novel end-to-end framework that comprehensively addresses the key sources of stochasticity in SVRP and utilizes an RL agent with a simple yet effective architecture and a tailored training method. Through comparative analysis, our proposed model demonstrates superior performance compared to a widely adopted state-of-the-art metaheuristic, achieving a significant 3.43% reduction in travel costs. Furthermore, the model exhibits robustness across diverse SVRP settings, highlighting its adaptability and ability to learn optimal routing strategies in varying environments. The publicly available implementation of our framework serves as a valuable resource for future research endeavors aimed at advancing RL-based solutions for SVRP.

Learning to generalize Dispatching rules on the Job Shop Scheduling

This paper introduces a Reinforcement Learning approach to better generalize heuristic dispatching rules on the Job-shop Scheduling Problem (JSP). Current models on the JSP do not focus on generalization, although, as we show in this work, this is key to learning better heuristics on the problem. A well-known technique to improve generalization is to learn on increasingly complex instances using Curriculum Learning (CL). However, as many works in the literature indicate, this technique might suffer from catastrophic forgetting when transferring the learned skills between different problem sizes. To address this issue, we introduce a novel Adversarial Curriculum Learning (ACL) strategy, which dynamically adjusts the difficulty level during the learning process to revisit the worst-performing instances. This work also presents a deep learning model to solve the JSP, which is equivariant w.r.t. the job definition and size-agnostic. Conducted experiments on Taillard's and Demirkol's instances show that the presented approach significantly improves the current state-of-the-art models on the JSP. It reduces the average optimality gap from 19.35\% to 10.46\% on Taillard's instances and from 38.43\% to 18.85\% on Demirkol's instances. Our implementation is available online.

AI for Porosity and Permeability Prediction from Geologic Core X-Ray Micro-Tomography

Geologic cores are rock samples that are extracted from deep under the ground during the well drilling process. They are used for petroleum reservoirs' performance characterization. Traditionally, physical studies of cores are carried out by the means of manual time-consuming experiments. With the development of deep learning, scientists actively started working on developing machine-learning-based approaches to identify physical properties without any manual experiments. Several previous works used machine learning to determine the porosity and permeability of the rocks, but either method was inaccurate or computationally expensive. We are proposing to use self-supervised pretraining of the very small CNN-transformer-based model to predict the physical properties of the rocks with high accuracy in a time-efficient manner. We show that this technique prevents overfitting even for extremely small datasets.

Robust Reinforcement Learning on Graphs for Logistics optimization

Logistics optimization nowadays is becoming one of the hottest areas in the AI community. In the past year, significant advancements in the domain were achieved by representing the problem in a form of graph. Another promising area of research was to apply reinforcement learning algorithms to the above task. In our work, we made advantage of using both approaches and apply reinforcement learning on a graph. To do that, we have analyzed the most recent results in both fields and selected SOTA algorithms both from graph neural networks and reinforcement learning. Then, we combined selected models on the problem of AMOD systems optimization for the transportation network of New York city. Our team compared three algorithms - GAT, Pro-CNN and PTDNet - to bring to the fore the important nodes on a graph representation. Finally, we achieved SOTA results on AMOD systems optimization problem employing PTDNet with GNN and training them in reinforcement fashion. Keywords: Graph Neural Network (GNN), Logistics optimization, Reinforcement Learning