Exploratory Combinatorial Optimization with Reinforcement Learning
arXiv:1909.04063
Abstract
Many real-world problems can be reduced to combinatorial optimization on a graph, where the subset or ordering of vertices that maximize some objective function must be found. With such tasks often NP-hard and analytically intractable, reinforcement learning (RL) has shown promise as a framework with which efficient heuristic methods to tackle these problems can be learned. Previous works construct the solution subset incrementally, adding one element at a time, however, the irreversible nature of this approach prevents the agent from revising its earlier decisions, which may be necessary given the complexity of the optimization task. We instead propose that the agent should seek to continuously improve the solution by learning to explore at test time. Our approach of exploratory combinatorial optimization (ECO-DQN) is, in principle, applicable to any combinatorial problem that can be defined on a graph. Experimentally, we show our method to produce state-of-the-art RL performance on the Maximum Cut problem. Moreover, because ECO-DQN can start from any arbitrary configuration, it can be combined with other search methods to further improve performance, which we demonstrate using a simple random search.
arXiv commentIn Proceedings of the 34th National Conference on Artificial Intelligence, AAAI 2020
References in corpus (9)
- Statistical mechanics of complex networks
- Neural Message Passing for Quantum Chemistry
- Learning Combinatorial Optimization Algorithms over Graphs
- Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search
- Reverse Quantum Annealing Approach to Portfolio Optimization Problems
- Destabilization of local minima in analog spin systems by correction of amplitude heterogeneity
- Learning Heuristics over Large Graphs via Deep Reinforcement Learning
- Gaussian Optical Ising Machines
- Solving NP-Hard Problems on Graphs with Extended AlphaGo Zero
Cited by in corpus (4)
- Quantum-inspired annealers as Boltzmann generators for machine learning and statistical physics
- Reinforcement Learning Enhanced Quantum-inspired Algorithm for Combinatorial Optimization
- Reversible Action Design for Combinatorial Optimization with Reinforcement Learning
- Deployment Optimization for Shared e-Mobility Systems with Multi-agent Deep Neural Search