AI RESEARCH
Automated Reinforcement Learning: An Overview
arXiv CS.LG
•
ArXi:2201.05000v2 Announce Type: replace Reinforcement Learning and, recently, Deep Reinforcement Learning are popular methods for solving sequential decision-making problems modeled as Marko Decision Processes. RL modeling of a problem and selecting algorithms and hyper-parameters require careful consideration, as different configurations may entail completely different performances.