Reinforcement Learning for Combinatorial Optimization: A Survey

Combinatorial optimization (CO) is the workhorse of numerous important applications in operations research, engineering, and other fields and, thus, has been attracting enormous attention from the research community recently. Some efficient approaches to common problems involve using hand-crafted heuristics to sequentially construct a solution. Therefore, it is intriguing to see how a CO problem can be reformulated as a sequential decision-making process, and whether these heuristics can be implicitly learned by a reinforcement learning (RL) agent. This survey explores the synergy between the CO and RL frameworks, which can become a promising direction for solving combinatorial problems.