ResearchBenchmarksRestless Multi-Armed Bandit Policy Optimization on Machine maintenance problem finite-horizonFollow-2.82Minimum Gain (%)RAWIP-29.7352-22.7476-15.76-8.7724Oct 30, 2024Evaluation ResultsMethodMethodLinksMinimum Gain (%)Maximum Gain (%)Average Gain (%)Percentage Above ZeroRAWIP2024.10-2.82182.620.395.3SSUP2024.10-28.7132.20.4849.1