A multi-step Q-learning algorithm was employed to overcome the slow convergence rate of standard Q-learning, and CMAC neural network was used to generalize the continuous state space.

 
  • 為解決連續過(guò)程的學(xué)習問(wèn)題,采用CMAC神經(jīng)網(wǎng)絡(luò )對連續狀態(tài)空間進(jìn)行泛化。
今日熱詞
目錄 附錄 查詞歷史
国内精品美女A∨在线播放xuan