Quantitative weighing system and quantitative weighing method

摘要

In the quantitative weighing system 1, when the total sum of the weights of the articles S in each station 2 is regarded as a state, when the sorting motion of the articles S with respect to each station 2 is taken as a transition and the change in the state due to the execution of actions is taken as a transition, The transition difficulty level indicating the difficulty of supplying the article S having the necessary weight is updated. Then, in the graph structure expressing the state transition model, the first reward which is higher as the transition difficulty level of each edge is lower and the sum of the weights of the articles S with respect to the transition destination node connected to each edge is If it is within the target range, the Q value set for each edge is updated so that the second reward is given.