Deep policy dynamic programming for vehicle routing problems
From MaRDI portal
Publication:2170197
Abstract: Routing problems are a class of combinatorial problems with many practical applications. Recently, end-to-end deep learning methods have been proposed to learn approximate solution heuristics for such problems. In contrast, classical dynamic programming (DP) algorithms guarantee optimal solutions, but scale badly with the problem size. We propose Deep Policy Dynamic Programming (DPDP), which aims to combine the strengths of learned neural heuristics with those of DP algorithms. DPDP prioritizes and restricts the DP state space using a policy derived from a deep neural network, which is trained to predict edges from example solutions. We evaluate our framework on the travelling salesman problem (TSP), the vehicle routing problem (VRP) and TSP with time windows (TSPTW) and show that the neural policy improves the performance of (restricted) DP algorithms, making them competitive to strong alternatives such as LKH, while also outperforming most other 'neural approaches' for solving TSPs, VRPs and TSPTWs with 100 nodes.
Recommendations
- Learning the travelling salesperson problem requires rethinking generalization
- Learning heuristics for the TSP by policy gradient
- Solving the traveling salesperson problem with precedence constraints by deep reinforcement learning
- A restricted dynamic programming heuristic algorithm for the time dependent traveling salesman problem
- TLHSA and SACA: two heuristic algorithms for two variant VRP models
Cites work
- A Dynamic Programming Approach to Sequencing Problems
- A Hybrid Genetic Algorithm for Multidepot and Periodic Vehicle Routing Problems
- A general VNS heuristic for the traveling salesman problem with time windows
- A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
- A note on two problems in connexion with graphs
- A restricted dynamic programming heuristic algorithm for the time dependent traveling salesman problem
- An Optimal Algorithm for the Traveling Salesman Problem with Time Windows
- An approximate dynamic programming approach for the vehicle routing problem with stochastic demands
- Deep learning assisted heuristic tree search for the container pre-marshalling problem
- Dynamic Programming Strategies for the Traveling Salesman Problem with Time Window and Precedence Constraints
- Dynamic Programming Treatment of the Travelling Salesman Problem
- Dynamic programming and optimal control. Vol. 1.
- Generalization of machine learning for problem reduction: a case study on travelling salesman problems
- Hybrid genetic search for the CVRP: open-source implementation and SWAP* neighborhood
- New benchmark instances for the capacitated vehicle routing problem
- On the Theory of Dynamic Programming
- Record breaking optimization results using the ruin and recreate principle
- Reinforcement learning for combinatorial optimization: a survey
- Restricted dynamic programming: a flexible framework for solving realistic VRPs
- Solving the job-shop scheduling problem optimally by dynamic programming
- The vehicle routing problem: An overview of exact and approximate algorithms
- Three-dimensional matching instances are rich in stable matchings
- Tour merging via branch-decomposition
- Vehicle Routing
Cited in
(14)- Predicting the optimal period for Cyclic Hoist Scheduling Problems
- Deep infeasibility exploration method for vehicle routing problems
- Learning heuristics for the TSP by policy gradient
- Solving the traveling salesperson problem with precedence constraints by deep reinforcement learning
- Dynamic graph conv-LSTM model with dynamic positional encoding for the large-scale traveling salesman problem
- Research on improved ant colony optimization for traveling salesman problem
- Solving large-scale routing optimization problems with networks and only networks
- Neural networks for local search and crossover in vehicle routing: a possible overkill?
- Neural large neighborhood search for routing problems
- A reinforcement learning approach to convoy scheduling on a contested transportation network
- Learning to repeatedly solve routing problems
- Opportunities for reinforcement learning in stochastic dynamic vehicle routing
- Learning the travelling salesperson problem requires rethinking generalization
- Learn and route: learning implicit preferences for vehicle routing
This page was built for publication: Deep policy dynamic programming for vehicle routing problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2170197)
