Review
Engineering, Chemical
Ruan de Rezende Faria, Bruno Didier Olivier Capron, Argimiro Resende Secchi, Mauricio B. de Souza Jr
Summary: This paper provides a literature review on the application of reinforcement learning in process control and optimization. It introduces new perspectives on simulation-based training, transfer learning, and online process control, and presents a framework for hyperparameter optimization to achieve feasible algorithms and deep neural networks. The study also demonstrates an experiment in batch process control using the deep-deterministic-policy-gradient algorithm modified with adversarial imitation learning.
Article
Management
Pengyu Yan, Kaize Yu, Xiuli Chao, Zhibin Chen
Summary: This study proposes a Markov decision process to optimize the charging and order-dispatching schemes for an e-hailing EV fleet. An online approximation algorithm is developed using the model-based reinforcement learning framework and a novel SARSA(A)-sample average approximation architecture. The proposed approach increases the daily revenue by an average of 31.76% and 14.22%, respectively, compared with existing methods.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2023)
Article
Computer Science, Theory & Methods
Fatemeh Abdi, Mahmood Ahmadi, Montajab Ghanem
Summary: This paper presents a new strategy to improve the forwarding of request packets in Named Data Networking (NDN), which improves the overall performance by considering experiences and using a Learning Automata-based algorithm.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Management
Guodong Yu, Aijun Liu, Jianghua Zhang, Huiping Sun
Summary: The paper discusses the operation planning problem in electric autonomous vehicle ride-hailing systems, utilizing a flexible policy and an asynchronous learning method to handle the curse-of-dimensionality caused by the large scale of state space and uncertainty. The model outperforms predetermined rules and managerial insights are extracted for ride-hailing operations planning.
OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE
(2021)
Article
Computer Science, Interdisciplinary Applications
Sefakor Fianu, Lauren B. Davis
Summary: We propose an algorithm to solve an infinite horizon nested Markov decision process under the average reward criterion. The algorithm incorporates the policy iteration method and is evaluated using a specialized enumerative algorithm.
COMPUTERS & OPERATIONS RESEARCH
(2023)
Article
Computer Science, Information Systems
Jing Yao, Zhicheng Dou, Jun Xu, Ji-Rong Wen
Summary: The article introduces a framework RLPS for personalized search using reinforcement learning, with models RLPS-L and RLPS-H that track user interactions with the search engine to continuously update personalized ranking models. Additionally, a feedback-aware personalized ranking component is designed to capture user feedback and impact the user's interest profile. Significant improvements over existing personalized search models are observed in experiments.
ACM TRANSACTIONS ON INFORMATION SYSTEMS
(2021)
Article
Automation & Control Systems
Mingsheng Fu, Liwei Huang, Ananya Rao, Athirai A. Irissappane, Jie Zhang, Hong Qu
Summary: Deep reinforcement learning (DRL) based recommender systems are suitable for user cold-start problems as they can progressively capture user preferences. However, most existing DRL-based recommender systems are suboptimal because they use the same policy for different users. To address this, we propose a multitask Markov Decision Process framework where each task represents a set of similar users. We use Q-learning to optimize the framework and consider task uncertainty through mutual information. Experiments on real-world datasets demonstrate the effectiveness of our approach.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Geochemistry & Geophysics
Chengliang Wu, Bo Feng, Huazhong Wang, Xiaonan Song, Shen Sheng, Rongwei Xu
Summary: This article proposes an effective and robust scheme for residual moveout (RMO) picking using a Markov decision process (MDP). The scheme is implemented on multiple common-image gathers (CIGs) to ensure accurate and reliable RMO data extraction. Experimental results demonstrate the effectiveness and validity of the proposed scheme.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
J. H. Ruan, Z. X. Wang, Felix T. S. Chan, S. Patnaik, M. K. Tiwari
Summary: With fierce competition in the airline industry, the study focuses on generating optimal maintenance routes for aircraft. A network flow-based ILP framework considering multiple maintenance constraints and a reinforcement learning algorithm have been proposed to efficiently solve the operational aircraft maintenance routing problem.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Minu Tiwari, Sudip Misra, Pradyumna Kumar Bishoyi, Laurence T. Yang
Summary: In this article, an efficient criticality-aware decision-making system named Devote is presented for fog-based Internet of Things (IoT) environment. Devote introduces an intelligent algorithm to prioritize data based on criticality and considers fog node (FN) resource availability. A reinforcement-learning-based algorithm is adopted to handle IoT data in dynamic conditions, along with an efficient online secretary-based algorithm for selecting the best FN candidate for data offloading. Devote demonstrates reduced service delay compared to other systems and achieves a user satisfaction rate of 88.4%.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Management
Uday M. Kumar, Sanjay P. Bhat, Veeraruna Kavitha, Nandyala Hemachandra
Summary: This paper deals with the problem of finding near-optimal Markovian randomized (MR) policies for constrained risk-sensitive Markov decision processes (CRSMDPs) with finite state-action sets and infinite horizons. It proves the existence of a solution to the optimization problem for CRSMDPs if feasible and provides two methods for finding a practical solution in the form of ultimately stationary (US) MR policies. These methods involve approximating finite-horizon CRSMDPs and ensuring that the violation of constraints is bounded above by a specified tolerance value. The paper also discusses applications and provides an example using an infinite-horizon risk-sensitive inventory control problem.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2023)
Article
Computer Science, Information Systems
Juan Parras, Alejandro Almodovar, Patricia A. Apellaniz, Santiago Zazo
Summary: The recent advances in Deep Learning have had a significant impact on wireless network security, with the emergence of intelligent attackers who can exploit defense mechanisms by interacting with them. This article proposes the development of two intelligent defense mechanisms using inverse reinforcement learning tools, which can enhance the capabilities of current defense mechanisms. The proposal shows significant gains in defense performance through experimentation with a backoff attack scenario against an intelligent attacker.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Engineering, Industrial
Chen Li, Qing Chang
Summary: A novel control method is proposed for multi-stage production systems to improve system efficiency by dynamically changing the cycle time of individual machines. The method integrates distributed feedback control with a reinforcement learning scheme, and shows significant improvements in overall profits and energy savings.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Tom Lefebvre, Guillaume Crevecoeur
Summary: This paper explores a special case of the Imitation from Observations problem, focusing on feature-only demonstrations. It introduces the concept of Imitation from Partial Observations and proposes a method called Behavioral Cloning for policy learning. The paper also presents a rational inference model based on a controlled Hidden Markov Model and applies Expectation-Maximization to solve the Maximum Likelihood Estimation problem. The results, named A Posteriori Control Densities, are compared to existing methods and further development opportunities are identified.
PATTERN RECOGNITION LETTERS
(2023)
Article
Computer Science, Artificial Intelligence
Tom Lefebvre
Summary: In this study, we extend and handle the problem of imitation from observations, specifically in the case of feature-only demonstrations. Our approach combines elements from probability and information theory to develop a behavioral cloning method that extracts an executable policy directly from the given features.
PATTERN RECOGNITION LETTERS
(2022)
Article
Transportation Science & Technology
Yue Zhao, Liujiang Kang, Huijun Sun, Jianjun Wu, Nsabimana Buhigiro
Summary: This study proposes a 2-population 3-strategy evolutionary game model to address the issue of subway network operation extension. The analysis reveals that the rule of maximum total fitness ensures the priority of evolutionary equilibrium strategies, and proper adjustment minutes can enhance the effectiveness of operation extension.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Hongtao Hu, Jiao Mob, Lu Zhen
Summary: This study investigates the challenges of daily storage yard management in marine container terminals considering delayed transshipment of containers. A mixed-integer linear programming model is proposed to minimize various costs associated with transportation and yard management. The improved Benders decomposition algorithm is applied to solve the problem effectively and efficiently.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Zhandong Xu, Yiyang Peng, Guoyuan Li, Anthony Chen, Xiaobo Liu
Summary: This paper studied the impact of range anxiety among electric vehicle drivers on traffic assignment. Two types of range-constrained traffic assignment problems were defined based on discrete or continuous distributed range anxiety. Models and algorithms were proposed to solve the two types of problems. Experimental results showed the superiority of the proposed algorithm and revealed that drivers with heightened range anxiety may cause severe congestion.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Chuanjia Li, Maosi Geng, Yong Chen, Zeen Cai, Zheng Zhu, Xiqun (Michael) Chen
Summary: Understanding spatial-temporal stochasticity in shared mobility is crucial, and this study introduces the Bi-STTNP prediction model that provides probabilistic predictions and uncertainty estimations for ride-sourcing demand, outperforming conventional deep learning methods. The model captures the multivariate spatial-temporal Gaussian distribution of demand and offers comprehensive uncertainty representations.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Benjamin Coifman, Lizhe Li
Summary: This paper develops a partial trajectory method for aligning views from successive fixed cameras in order to ensure high fidelity with the actual vehicle movements. The method operates on the output of vehicle tracking to provide direct feedback and improve alignment quality. Experimental results show that this method can enhance accuracy and increase the number of vehicles in the dataset.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Mohsen Dastpak, Fausto Errico, Ola Jabali, Federico Malucelli
Summary: This article discusses the problem of an Electric Vehicle (EV) finding the shortest route from an origin to a destination and proposes a problem model that considers the occupancy indicator information of charging stations. A Markov Decision Process formulation is presented to optimize the EV routing and charging policy. A reoptimization algorithm is developed to establish the sequence of charging station visits and charging amounts based on system updates. Results from a comprehensive computational study show that the proposed method significantly reduces waiting times and total trip duration.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)