A Survey on Reinforcement Learning for Combinatorial Optimization

17 Aug 2020  ·  Yunhao Yang, Andrew Whinston ·

This paper gives a detailed review of reinforcement learning in combinatorial optimization, introduces the history of combinatorial optimization starting in the 1960s, and compares it with the reinforcement learning algorithms in recent years. We explicitly look at a famous combinatorial problem known as the Traveling Salesperson Problem (TSP)... We compare the approach of the modern reinforcement learning algorithms on TSP with an approach published in 1970. Then, we discuss the similarities between these algorithms and how the approach of reinforcement learning changes due to the evolution of machine learning techniques and computing power. We also mention the deep learning approach on the TSP, which is named Deep Reinforcement Learning. We argue that deep learning is a generic approach that can be integrated with traditional reinforcement learning algorithms and optimize the outcomes of the TSP. read more

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here