VaP-CSMV uses a cross-semantic encoder and multi-view decoder to unify DRL solving of HFVRP variants, outperforming prior neural solvers while matching heuristics at much lower inference time and generalizing zero-shot to unseen scales.
hub
Attention, learn to solve routing problems!
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
abstract
The recently presented idea to learn heuristics for combinatorial optimization problems is promising as it can save costly development. However, to push this idea towards practical implementation, we need better models and better ways of training. We contribute in both directions: we propose a model based on attention layers with benefits over the Pointer Network and we show how to train this model using REINFORCE with a simple baseline based on a deterministic greedy rollout, which we find is more efficient than using a value function. We significantly improve over recent learned heuristics for the Travelling Salesman Problem (TSP), getting close to optimal results for problems up to 100 nodes. With the same hyperparameters, we learn strong heuristics for two variants of the Vehicle Routing Problem (VRP), the Orienteering Problem (OP) and (a stochastic variant of) the Prize Collecting TSP (PCTSP), outperforming a wide range of baselines and getting results close to highly optimized and specialized algorithms.
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
A graph neural network learns to approximate altruistic robot transfers across heterogeneous teams using Hamilton's rule, achieving near-optimal allocation in simulated firefighting scenarios.
Reinforcement learning policy for qubit mapping reduces SWAP overhead by 65-85% versus standard quantum compilers on MQTBench and Queko benchmark circuits.
ECO uses supervised warm-up plus iterative batched DPO on a Mamba backbone to reach top neural performance on TSP and CVRP while lowering memory growth and raising throughput.
QARMA applies transformer-augmented reinforcement learning to qubit allocation and reuse in modular quantum systems, reporting up to 86% average reduction in inter-core communications versus optimized Qiskit baselines.
Classical solver KaMIS outperforms leading AI methods for Maximum Independent Set on random graphs, with some AI approaches no better than simple greedy heuristics and a new serialization analysis revealing similar reasoning.
An attention-based DRL agent with Transformer encoder and GNN learns heuristics for qubit-to-core allocation in multi-core quantum systems to minimize state transfers and online compilation time.
A two-stage ML sparsifier for TSP candidate graphs combines alpha-Nearest and POPMUSIC for high recall then trains a model to cut density while preserving coverage across distance types and instance sizes up to 500.
Fine-tuned LLMs with DAR sampling and DPO outperform off-the-shelf versions on algorithm design tasks and generalize to related settings.
RouteFormer is a transformer-RL hybrid for single-agent graph routing that reports 10% and 7% shorter distances than Concorde and LKH-3 on mission-like graphs by incorporating constraints the solvers ignore.
ARMATA is a new end-to-end autoregressive model with multi-stage decoding that unifies allocation and routing for multi-agent systems and reports up to 20% better solutions than OR-Tools, CPLEX, and LKH-3 in seconds instead of hours.
Adding simulated annealing to random reconstruction and beam search to POMO in neural CVRP solvers reduces optimality gaps on standard benchmarks.
A tutorial framing deep learning as a complement to optimization for sequential decision-making under uncertainty, with applications in supply chains, healthcare, and energy.
citing papers explorer
-
Vehicle-as-Prompt: A Unified Deep Reinforcement Learning Framework for Heterogeneous Fleet Vehicle Routing Problem
VaP-CSMV uses a cross-semantic encoder and multi-view decoder to unify DRL solving of HFVRP variants, outperforming prior neural solvers while matching heuristics at much lower inference time and generalizing zero-shot to unseen scales.
-
Learning Altruistic Collaboration in Heterogeneous Multi-Team Systems
A graph neural network learns to approximate altruistic robot transfers across heterogeneous teams using Hamilton's rule, achieving near-optimal allocation in simulated firefighting scenarios.
-
CO-MAP: A Reinforcement Learning Approach to the Qubit Allocation Problem
Reinforcement learning policy for qubit mapping reduces SWAP overhead by 65-85% versus standard quantum compilers on MQTBench and Queko benchmark circuits.
-
Rethinking Efficiency in Neural Combinatorial Optimization: Batched Preference Optimization with Mamba
ECO uses supervised warm-up plus iterative batched DPO on a Mamba backbone to reach top neural performance on TSP and CVRP while lowering memory growth and raising throughput.
-
Learning-Optimized Qubit Mapping and Reuse to Minimize Inter-Core Communication in Modular Quantum Architectures
QARMA applies transformer-augmented reinforcement learning to qubit allocation and reuse in modular quantum systems, reporting up to 86% average reduction in inter-core communications versus optimized Qiskit baselines.
-
Unrealized Expectations: Comparing AI Methods vs Classical Algorithms for Maximum Independent Set
Classical solver KaMIS outperforms leading AI methods for Maximum Independent Set on random graphs, with some AI approaches no better than simple greedy heuristics and a new serialization analysis revealing similar reasoning.
-
Attention-Based Deep Reinforcement Learning for Qubit Allocation in Modular Quantum Architectures
An attention-based DRL agent with Transformer encoder and GNN learns heuristics for qubit-to-core allocation in multi-core quantum systems to minimize state transfers and online compilation time.
-
Machine Learning for Two-Stage Graph Sparsification for the Travelling Salesman Problem
A two-stage ML sparsifier for TSP candidate graphs combines alpha-Nearest and POPMUSIC for high recall then trains a model to cut density while preserving coverage across distance types and instance sizes up to 500.
-
Fine-tuning Large Language Model for Automated Algorithm Design
Fine-tuned LLMs with DAR sampling and DPO outperform off-the-shelf versions on algorithm design tasks and generalize to related settings.
-
RouteFormer: A Transformer-Based Routing Framework for Autonomous Vehicles
RouteFormer is a transformer-RL hybrid for single-agent graph routing that reports 10% and 7% shorter distances than Concorde and LKH-3 on mission-like graphs by incorporating constraints the solvers ignore.
-
ARMATA: Auto-Regressive Multi-Agent Task Assignment
ARMATA is a new end-to-end autoregressive model with multi-stage decoding that unifies allocation and routing for multi-agent systems and reports up to 20% better solutions than OR-Tools, CPLEX, and LKH-3 in seconds instead of hours.
-
NCO4CVRP: Neural Combinatorial Optimization for the Capacitated Vehicle Routing Problem
Adding simulated annealing to random reconstruction and beam search to POMO in neural CVRP solvers reduces optimality gaps on standard benchmarks.
-
Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers
A tutorial framing deep learning as a complement to optimization for sequential decision-making under uncertainty, with applications in supply chains, healthcare, and energy.
- Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear Programming