Automatic Verification Flow Shop Scheduling of Electric Energy Meters Based on an Improved Q-Learning Algorithm

Considering the engineering problem of electric energy meter automatic verification and scheduling, this paper proposes a novel scheduling scheme based on an improved Q-learning algorithm. First, by introducing state variables behavior variables, ranking combinatorial optimization is transformed into sequential decision problem. Then, reward function proposed to evaluate pros cons different strategies. In particular, considers adopting reinforcement learning algorithm efficiently solve addition, also ratio exploration utilization in process, then provides reasonable through iterative updating scheme. Meanwhile, decoupling strategy introduced address restriction over estimation. Finally, real time data from provincial center are used verify effectiveness