Verifying the differences of the action selections for the action planning problem of AGVs by applying the reinforcement learning

Reinforcement learning is often used to solve AGVs problems, such as luggage transportation. Softmax policy and $\epsilon$-greedy policy are typical policies for action selection in reinforcement learning. In this study, we verify the transport efficiency of AGVs for the two types of action selection and verify a method that combines the two types of action selection.