paper-with-me

Papers

POMO: Policy Optimization with Multiple Optima for Reinforcement Learning

2020-10-30 · NeurIPS 2020 12 · Yeong-Dae Kwon, Jinho Choo, Byoungjip Kim, Iljoo Yoon, Youngjune Gwon, Seungjai Min

In neural combinatorial optimization (CO), reinforcement learning (RL) can turn a deep neural net into a fast, powerful heuristic solver of NP-hard problems. This approach has a great potential in practical applications because it allows near-optimal solutions to be found without expert guides armed with substantial domain knowledge. We introduce Policy Optimization with Multiple Optima (POMO), an end-to-end approach for building such a heuristic solver. POMO is applicable to a wide range of CO problems. It is designed to exploit the symmetries in the representation of a CO solution. POMO uses a modified REINFORCE algorithm that forces diverse rollouts towards all optimal solutions. Empirically, the low-variance baseline of POMO makes RL training fast and stable, and it is more resistant to local minima compared to previous approaches. We also introduce a new augmentation-based inference method, which accompanies POMO nicely. We demonstrate the effectiveness of POMO by solving three popular NP-hard problems, namely, traveling salesman (TSP), capacitated vehicle routing (CVRP), and 0-1 knapsack (KP). For all three, our solver based on POMO shows a significant improvement in performance over all recent learned heuristics. In particular, we achieve the optimality gap of 0.14% with TSP100 while reducing inference time by more than an order of magnitude.

📄 PDF Abstract BibTeX arXiv:2010.16011

Code (3)

yd-kwon/POMO 공식 구현 pytorch
ahottung/EAS pytorch
kaist-silab/symmetric_replay pytorch

Tasks

Combinatorial Optimizationreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

POMO 설명 없음
REINFORCE REINFORCE is a Monte Carlo variant of a policy gradient algorithm in reinforcement learning. The agent collects samples of an episode using its current policy, and uses it to…

Similar Papers 제목 키워드 기반

Leader Reward for POMO-Based Neural Combinatorial Optimization

2024-05-22 · Chaoyang Wang, Pengzhi Cheng, Jingze Li, Weiwei Sun

Deep neural networks based on reinforcement learning (RL) for solving combinatorial optimization (CO) problems are developing rapidly and have shown a tendency to approach or even outperform traditional solvers. However,…

Combinatorial OptimizationReinforcement Learning (RL)Traveling Salesman Problem

Generative Adversarial Training for Neural Combinatorial Optimization Models

2021-09-29 · Liang Xin, Wen Song, Zhiguang Cao, Jie Zhang

Recent studies show that deep neural networks can be trained to learn good heuristics for various Combinatorial Optimization Problems (COPs). However, it remains a great challenge for the trained deep optimization models…

Combinatorial OptimizationTraveling Salesman Problem

Synergizing Reinforcement Learning and Genetic Algorithms for Neural Combinatorial Optimization

2025-06-11 · Shengda Gu, Kai Li, Junliang Xing, Yifan Zhang 외

Combinatorial optimization problems are notoriously challenging due to their discrete structure and exponentially large solution space. Recent advances in deep reinforcement learning (DRL) have enabled the learning heuri…

Combinatorial OptimizationDeep Reinforcement LearningEvolutionary Algorithmsreinforcement-learning+1

Learn to Solve Vehicle Routing Problems ASAP: A Neural Optimization Approach for Time-Constrained Vehicle Routing Problems with Finite Vehicle Fleet

2024-11-07 · Elija Deineko, Carina Kehrt

Finding a feasible and prompt solution to the Vehicle Routing Problem (VRP) is a prerequisite for efficient freight transportation, seamless logistics, and sustainable mobility. Traditional optimization methods reach the…

BenchmarkingCombinatorial OptimizationDecoder

POMONAG: Pareto-Optimal Many-Objective Neural Architecture Generator

2024-09-30 · Eugenio Lomurno, Samuele Mariani, Matteo Monti, Matteo Matteucci

Neural Architecture Search (NAS) automates neural network design, reducing dependence on human expertise. While NAS methods are computationally intensive and dataset-specific, auxiliary predictors reduce the models needi…

Computational Efficiencyimage-classificationImage ClassificationNeural Architecture Search