Deep learning assisted heuristic tree search for the container pre-marshalling problem
From MaRDI portal
Publication:2333140
Abstract: The container pre-marshalling problem (CPMP) is concerned with the re-ordering of containers in container terminals during off-peak times so that containers can be quickly retrieved when the port is busy. The problem has received significant attention in the literature and is addressed by a large number of exact and heuristic methods. Existing methods for the CPMP heavily rely on problem-specific components (e.g., proven lower bounds) that need to be developed by domain experts with knowledge of optimization techniques and a deep understanding of the problem at hand. With the goal to automate the costly and time-intensive design of heuristics for the CPMP, we propose a new method called Deep Learning Heuristic Tree Search (DLTS). It uses deep neural networks to learn solution strategies and lower bounds customized to the CPMP solely through analyzing existing (near-) optimal solutions to CPMP instances. The networks are then integrated into a tree search procedure to decide which branch to choose next and to prune the search tree. DLTS produces the highest quality heuristic solutions to the CPMP to date with gaps to optimality below 2% on real-world sized instances.
Recommendations
- Solving real-world sized container pre-marshalling problems with an iterative deepening branch-and-bound algorithm
- A tree search procedure for the container pre-marshalling problem
- Solving the robust container pre-marshalling problem
- A feasibility-based heuristic for the container pre-marshalling problem
- A branch and bound approach for large pre-marshalling problems
Cites work
- A biased random-key genetic algorithm for the container pre-marshalling problem
- A branch and bound approach for large pre-marshalling problems
- A branch and price procedure for the container premarshalling problem
- A feasibility-based heuristic for the container pre-marshalling problem
- A machine learning-based approximation of strong branching
- A multi-heuristic approach for solving the pre-marshalling problem
- A tree search procedure for the container pre-marshalling problem
- Accelerating the branch-and-price algorithm using machine learning
- Algorithm selection for combinatorial search problems: a survey
- An exact algorithm for the blocks relocation problem with new lower bounds
- An optimization model for the container pre-marshalling problem
- Applying the corridor method to a blocks relocation problem
- ASlib: a benchmark library for algorithm selection
- Comments on: ``On learning and branching: a survey
- Crew assignment via constraint programming: Integrating column generation and heuristic tree search
- DASH: dynamic approach for switching heuristics
- Deep learning
- Embedding decision trees and random forests in constraint programming
- Empirical decision model learning
- Future paths for integer programming and links to artificial intelligence
- Learning when to use a decomposition
- Markov chain methods for the bipartite Boolean quadratic programming problem
- Model agnostic solution of CSPs via deep learning: a preliminary study
- New approaches for heuristic search: A bilateral linkage with artificial intelligence
- On learning and branching: a survey
- On the abstraction method for the container relocation problem
- Search-based structured prediction
- Solving real-world sized container pre-marshalling problems with an iterative deepening branch-and-bound algorithm
Cited in
(29)- Machine learning meets mathematical optimization to predict the optimal production of offshore wind parks
- Machine learning for combinatorial optimization: a methodological tour d'horizon
- Neural large neighborhood search for routing problems
- Deep policy dynamic programming for vehicle routing problems
- Robust optimization for premarshalling with uncertain priority classes
- A feature-extraction-based lightweight convolutional and recurrent neural networks adaptive computing model for container terminal liner handling volume forecasting
- A branch and bound approach for large pre-marshalling problems
- Pre-processing a container yard under limited available time
- A weighted-sum method for solving the bi-objective traveling thief problem
- A beam search algorithm for minimizing crane times in premarshalling problems
- Optimizing the number of deployed yard cranes in a container terminal
- An actor-critic algorithm with policy gradients to solve the job shop scheduling problem using deep double recurrent agents
- A constraint programming approach for the premarshalling problem
- Machine learning augmented approaches for hub location problems
- Novel models and algorithms for location assignment for outbound containers in container terminals
- The synergistic effect of operational research and big data analytics in greening container terminal operations: a review and future directions
- Integer programming model and branch-and-cut algorithm for the stack inbound and pre-marshalling problem
- A tree search algorithm for uncertainty-considered consecutive discharging and loading operations between ship and offshore platform
- Learning to sample initial solution for solving 0-1 discrete optimization problem by local search
- The container premarshalling problem under limited crane time: a constraint programming approach
- One-shot learning for MIPs with SOS1 constraints
- A deep reinforcement learning assisted simulated annealing algorithm for a maintenance planning problem
- Global optimization: a machine learning approach
- A deep reinforcement learning based multi-agent simulation optimization approach for IGV bidirectional task allocation and charging joint scheduling in automated container terminals
- MILP acceleration: a survey from perspectives of simplex initialization and learning-based branch and bound
- The first mile is the hardest: a deep learning-assisted matheuristic for container assignment in first-mile logistics
- Decision-focused neural adaptive search and diving for optimizing mining complexes
- Neural network assisted branch and bound algorithm for dynamic berth allocation problems
- Container pre-Marshalling problem under the same-group exclusive strategy
This page was built for publication: Deep learning assisted heuristic tree search for the container pre-marshalling problem
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2333140)
