Only given cycle state q learning phase optimization model, not the variable cycle, want to explore the case of variable cycle q learning phase to optimize the performance of the model to be studied further.

Only a cycle of learning Q skew optimization model, not to the variable cycle of research, and would like to explore the same cycle of learning skew Q optimized the performance of the model, for further study.

正在翻譯，請等待...

Only study cycle status of optimal model of Q-learning phase, no study of variable cycle, wanted to explore the cycle performance of Q-learning phase optimization model under the situation, pending further study.

Only studied has decided under the cyclical condition the Q study phase difference optimization model, has not conducted the research to the variable cycle situation, wanted to explore in the variable period situation the Q study phase difference optimization model performance, the pending further s