BQ-NCO: Bisimulation Quotienting for Generalizable Neural Combinatorial Optimization

by   Darko Drakulic, et al.

Despite the success of Neural Combinatorial Optimization methods for end-to-end heuristic learning, out-of-distribution generalization remains a challenge. In this paper, we present a novel formulation of combinatorial optimization (CO) problems as Markov Decision Processes (MDPs) that effectively leverages symmetries of the CO problems to improve out-of-distribution robustness. Starting from the standard MDP formulation of constructive heuristics, we introduce a generic transformation based on bisimulation quotienting (BQ) in MDPs. This transformation allows to reduce the state space by accounting for the intrinsic symmetries of the CO problem and facilitates the MDP solving. We illustrate our approach on the Traveling Salesman, Capacitated Vehicle Routing and Knapsack Problems. We present a BQ reformulation of these problems and introduce a simple attention-based policy network that we train by imitation of (near) optimal solutions for small instances from a single distribution. We obtain new state-of-the-art generalization results for instances with up to 1000 nodes from synthetic and realistic benchmarks that vary both in size and node distributions.


page 1

page 2

page 3

page 4


On the Generalization of Neural Combinatorial Optimization Heuristics

Neural Combinatorial Optimization approaches have recently leveraged the...

Attention Solves Your TSP

We propose a framework for solving combinatorial optimization problems o...

Towards Generalizable Neural Solvers for Vehicle Routing Problems via Ensemble with Transferrable Local Policy

Machine learning has been adapted to help solve NP-hard combinatorial op...

Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets

Combinatorial optimization (CO) problems are often NP-hard and thus out ...

Constrained Combinatorial Optimization with Reinforcement Learning

This paper presents a framework to tackle constrained combinatorial opti...

Understanding Curriculum Learning in Policy Optimization for Solving Combinatorial Optimization Problems

Over the recent years, reinforcement learning (RL) has shown impressive ...

Learning TSP Requires Rethinking Generalization

End-to-end training of neural network solvers for combinatorial problems...

Please sign up or login with your details

Forgot password? Click here to reset