About

Joe Geunes is an Associate Department Head for Graduate Affairs in the Department of Industrial & Systems Engineering at Texas A&M University. He holds a Ph.D. in Business Administration with a focus on Management Science and Operations Research from The Pennsylvania State University, earned in 1999, and an M.B.A. from the same institution obtained in 1993. His research interests encompass production and logistics planning, supply chain management, and operations. Dr. Geunes has been recognized as a Fellow of the Institute of Industrial Engineers since 2015 and has received multiple awards for his scholarly contributions, including the Marilyn and L. David Black Faculty Fellowship at Texas A&M University in 2022. His work has significantly contributed to the fields of operations research and industrial engineering, with a focus on optimizing supply chain processes and production systems.

Research topics

• Computer Science
• Operations research
• Business
• Mathematical optimization
• Microeconomics
• Mathematics
• Industrial organization
• Engineering
• Economics
• Marketing
• Process management
• Operations management

Selected publications

• A Novel Hybrid Heuristic-Reinforcement Learning Optimization Approach for a Class of Railcar Shunting Problems

  Open MIND · 2026-03-05

  preprintSenior author

  Railcar shunting is a core planning task in freight railyards, where yard planners need to disassemble and reassemble groups of railcars to form outbound trains. Classification tracks with access from one side only can be considered as stack structures, where railcars are added and removed from only one end, leading to a last-in-first-out (LIFO) retrieval order. In contrast, two-sided tracks function like queue structures, allowing railcars to be added from one end and removed from the opposite end, following a first-in-first-out (FIFO) order. We consider a problem requiring assembly of multiple outbound trains using two locomotives in a railyard with two-sided classification track access. To address this combinatorially challenging problem class, we decompose the problem into two subproblems, each with one-sided classification track access and a locomotive on each side. We present a novel Hybrid Heuristic-Reinforcement Learning (HHRL) framework that integrates railway-specific heuristic solution approaches with a reinforcement learning method, specifically Q-learning. The proposed framework leverages methods to decrease the state-action space and guide exploration during reinforcement learning. The results of a series of numerical experiments demonstrate the efficiency and quality of the HHRL algorithm in both one-sided access, single-locomotive problems and two-sided access, two-locomotive problems.

  DOI

• A Novel Hybrid Heuristic-Reinforcement Learning Optimization Approach for a Class of Railcar Shunting Problems

  ArXiv.org · 2026-03-05

  articleOpen accessSenior author

  Railcar shunting is a core planning task in freight railyards, where yard planners need to disassemble and reassemble groups of railcars to form outbound trains. Classification tracks with access from one side only can be considered as stack structures, where railcars are added and removed from only one end, leading to a last-in-first-out (LIFO) retrieval order. In contrast, two-sided tracks function like queue structures, allowing railcars to be added from one end and removed from the opposite end, following a first-in-first-out (FIFO) order. We consider a problem requiring assembly of multiple outbound trains using two locomotives in a railyard with two-sided classification track access. To address this combinatorially challenging problem class, we decompose the problem into two subproblems, each with one-sided classification track access and a locomotive on each side. We present a novel Hybrid Heuristic-Reinforcement Learning (HHRL) framework that integrates railway-specific heuristic solution approaches with a reinforcement learning method, specifically Q-learning. The proposed framework leverages methods to decrease the state-action space and guide exploration during reinforcement learning. The results of a series of numerical experiments demonstrate the efficiency and quality of the HHRL algorithm in both one-sided access, single-locomotive problems and two-sided access, two-locomotive problems.

  PublisherOA PDF

• Revisiting continuous <i>p</i> -hub location problems with the <b>ℓ</b> ¹ metric

  IISE Transactions · 2026-02-03

  article
  PublisherDOI

• A Novel Hybrid Heuristic–Reinforcement Learning Optimization Approach for a Class of Railcar Shunting Problems

  SSRN Electronic Journal · 2026-01-01

  preprintOpen accessSenior author
  PublisherDOI

• Policies for multi-trip route planning in time-sensitive environments

  Optimization Letters · 2025-07-23

  article
  PublisherDOI

• The price of flexibility in electricity markets

  Energy Economics · 2025-08-29

  articleSenior author
  PublisherDOI

• Optimizing Railcar Movements to Create Outbound Trains in a Freight Railyard

  ArXiv.org · 2025-05-10

  preprintOpen access

  A typical freight railyard at a manufacturing facility contains multiple tracks used for storage, classification, and outbound train assembly. Individual railcar storage locations on classification tracks are often determined before knowledge of their destination locations is known, giving rise to railcar shunting or switching problems, which require retrieving subsets of cars distributed throughout the yard to assemble outbound trains. To address this combinatorially challenging problem class, we propose a large-scale mixed-integer programming model that tracks railcar movements and corresponding costs over a finite planning horizon. The model permits simultaneous movement of multiple car groups via a locomotive and seeks to minimize repositioning costs. We also provide a dynamic programming formulation of the problem, demonstrate the NP-hardness of the corresponding optimization problem, and present an adaptive railcar grouping dynamic programming (ARG-DP) heuristic, which groups railcars with common destinations for efficient moves. Average results from a series of numerical experiments demonstrate the efficiency and quality of the ARG-DP algorithm in both simulated yards and a real yard. On average, across 60 test cases of simulated yards, the ARG-DP algorithm obtains solutions 355 times faster than solving the mixed-integer programming model using a commercial solver, while finding an optimal solution in 60% of the instances and maintaining an average optimality gap of 6.65%. In 10 cases based on the Gaia railyard in Portugal, the ARG-DP algorithm achieves solutions 229 times faster on average, finding an optimal solution in 50% of the instances with an average optimality gap of 6.90%.

  PublisherOA PDFDOI

• Repair Crew Routing for Infrastructure Network Restoration under Incomplete Information

  ArXiv.org · 2025-05-08

  preprintOpen accessSenior author

  This paper considers a disrupted infrastructure network where the repair crew knows the locations of service outages but not the locations of actual faults. Our goal is to determine a route for a single crew to visit and repair the disruptions to restore service with minimum negative impact. We call this problem the Traveling Repairman Network Restoration Problem (TRNRP). This problem presents strong computational challenges due to the combinatorial nature of the decisions, inter-dependencies within the underlying infrastructure network, and incomplete information. Considering the dynamic nature of the decisions as a result of dynamic information revelation on the status of the nodes, we model this problem as a finite-horizon Markov decision process. Our solution approach uses value approximation based on reinforcement learning, which is strengthened by structural results that identify a set of suboptimal moves. In addition, we propose state aggregation methods to reduce the size of the state space. We perform extensive computational studies to characterize the performance of our solution methods under different parameter settings and to compare them with benchmark solution approaches.

  PublisherOA PDFDOI

• Revisiting Continuous p-Hub Location Problems with the L1 Metric

  ArXiv.org · 2025-01-14

  preprintOpen access

  Motivated by emerging urban applications in commercial, public sector, and humanitarian logistics, we revisit continuous $p$-hub location problems in which several facilities must be located in a continuous space such that the expected minimum Manhattan travel distance from a random service provider to a random customer through exactly one hub facility is minimized. In this paper, we begin by deriving closed-form results for a one-dimensional case and two-dimensional cases with up to two hubs. Subsequently, a simulation-based approximation method is proposed for more complex two-dimensional scenarios with more than two hubs. Moreover, an extended problem with multiple service providers is analyzed to reflect real-life service settings. Finally, we apply our model and approximation method using publicly available data as a case study to optimize the deployment of public-access automated external defibrillators in Virginia Beach.

  PublisherOA PDFDOI

• Adjusted distributionally robust bounds on expected loss functions

  Computers & Operations Research · 2025-04-17 · 1 citations

  articleOpen accessSenior author

  Optimization problems in operations and finance often include a cost that is proportional to the expected amount by which a random variable exceeds some fixed quantity, known as the expected loss function. Representation of this function often leads to computational challenges, depending on the distribution of the random variable of interest. Moreover, in practice, a decision maker may possess limited information about this probability distribution, such as the mean and variance, but not the exact form of the associated probability density or distribution function. In such cases, a distributionally robust (DR) optimization approach seeks to minimize the maximum expected cost among all possible distributions that are consistent with the available information. Past research has recognized the overly conservative nature of this approach because it accounts for worst-case probability distributions that almost surely do not arise in practice. Motivated by this, we propose a DR approach that accounts for the worst-case performance with respect to a broad class of common continuous probability distributions, while producing solutions that are less conservative (and, therefore, less expensive, on average) than those produced by existing DR approaches in the literature. The methods we propose also permit approximation of the expected loss function for probability distributions under which exact representation of the function is difficult or impossible. Finally, we draw a connection between Scarf-type bounds from the literature, and mean-MAD (mean absolute deviation) bounds when MAD information is available in addition to variance.

  PublisherDOI

Recent grants

• Optimizing Linkages in Multistage Production/Distribution Systems

  NSF · $168k · 2003–2007

• Collaborative Research: Mitigating the Cost of Anarchy in Complex Supply Chain Systems

  NSF · $172k · 2009–2013

Frequent coauthors

• H. Edwin Romeijn

  26 shared

• Yasemin Merzifonluoğlu

  Tilburg University

  11 shared

• Kevin Taaffe

  10 shared

• Dinçer Konur

  Texas State University

  7 shared

• Bibo Yang

  Hong Kong Polytechnic University

  6 shared

• Mike Prince

  5 shared

• J. Cole Smith

  Syracuse University

  5 shared

• Pãnos M. Pardalos

  University of Florida

  4 shared

Awards & honors

• Fellow, Institute of Industrial Engineers (2015)
• Marilyn and L. David Black Faculty Fellow, Texas A&M Univers…
• Best Reviewer Award, Omega - The International Journal of Ma…
• Best Application Paper, Institute of Industrial and Systems…
• Best Paper Award, Production Planning and Scheduling Track,…