摘要:
参考: https://blog.csdn.net/int_main_Roland/article/details/124650909 给出实现代码: def get_kl(): mean0, log_std0, std0 = policy_net(Variable(states)) mean1 = 阅读全文
posted @ 2024-02-26 21:55
Angry_Panda
阅读(134)
评论(0)
推荐(0)
浙公网安备 33010602011771号