Improving Generalization of Deep Reinforcement Learning-based TSP Solvers

10/06/2021
by   Wenbin Ouyang, et al.
0

Recent work applying deep reinforcement learning (DRL) to solve traveling salesman problems (TSP) has shown that DRL-based solvers can be fast and competitive with TSP heuristics for small instances, but do not generalize well to larger instances. In this work, we propose a novel approach named MAGIC that includes a deep learning architecture and a DRL training method. Our architecture, which integrates a multilayer perceptron, a graph neural network, and an attention model, defines a stochastic policy that sequentially generates a TSP solution. Our training method includes several innovations: (1) we interleave DRL policy gradient updates with local search (using a new local search technique), (2) we use a novel simple baseline, and (3) we apply curriculum learning. Finally, we empirically demonstrate that MAGIC is superior to other DRL-based methods on random TSP instances, both in terms of performance and generalizability. Moreover, our method compares favorably against TSP heuristics and other state-of-the-art approach in terms of performance and computational time.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/07/2021

Generalization in Deep RL for TSP Problems via Equivariance and Local Search

Deep reinforcement learning (RL) has proved to be a competitive heuristi...
research
06/20/2023

Neural Inventory Control in Networks via Hindsight Differentiable Policy Optimization

Inventory management offers unique opportunities for reliably evaluating...
research
04/03/2020

Learning 2-opt Heuristics for the Traveling Salesman Problem via Deep Reinforcement Learning

Recent works using deep learning to solve the Traveling Salesman Problem...
research
02/27/2023

A Reinforcement Learning Approach for Scheduling Problems With Improved Generalization Through Order Swapping

The scheduling of production resources (such as associating jobs to mach...
research
02/22/2018

Structured Control Nets for Deep Reinforcement Learning

In recent years, Deep Reinforcement Learning has made impressive advance...
research
05/17/2023

Curriculum Learning in Job Shop Scheduling using Reinforcement Learning

Solving job shop scheduling problems (JSSPs) with a fixed strategy, such...
research
04/25/2020

A State Aggregation Approach for Solving Knapsack Problem with Deep Reinforcement Learning

This paper proposes a Deep Reinforcement Learning (DRL) approach for sol...

Please sign up or login with your details

Forgot password? Click here to reset