English

Reinforcement Learning Enhanced Quantum-inspired Algorithm for Combinatorial Optimization

Machine Learning 2021-03-22 v2 Artificial Intelligence Machine Learning

Abstract

Quantum hardware and quantum-inspired algorithms are becoming increasingly popular for combinatorial optimization. However, these algorithms may require careful hyperparameter tuning for each problem instance. We use a reinforcement learning agent in conjunction with a quantum-inspired algorithm to solve the Ising energy minimization problem, which is equivalent to the Maximum Cut problem. The agent controls the algorithm by tuning one of its parameters with the goal of improving recently seen solutions. We propose a new Rescaled Ranked Reward (R3) method that enables stable single-player version of self-play training that helps the agent to escape local optima. The training on any problem instance can be accelerated by applying transfer learning from an agent trained on randomly generated problems. Our approach allows sampling high-quality solutions to the Ising problem with high probability and outperforms both baseline heuristics and a black-box hyperparameter optimization approach.

Keywords

Cite

@article{arxiv.2002.04676,
  title  = {Reinforcement Learning Enhanced Quantum-inspired Algorithm for Combinatorial Optimization},
  author = {Dmitrii Beloborodov and A. E. Ulanov and Jakob N. Foerster and Shimon Whiteson and A. I. Lvovsky},
  journal= {arXiv preprint arXiv:2002.04676},
  year   = {2021}
}

Comments

Submitted to ICML 2020. 9 pages, 3 pdf figures. V2: fixed acknowledgements