dqn_agent.py 文件源码

def __init__(self, n_history, n_action, on_gpu=False):
        self.n_history = n_history
        self.n_action = n_action
        self.on_gpu = on_gpu
        super(Q, self).__init__(
            l1=F.Convolution2D(n_history, 32, ksize=8, stride=4, nobias=False, wscale=np.sqrt(2)),
            l2=F.Convolution2D(32, 64, ksize=3, stride=2, nobias=False, wscale=np.sqrt(2)),
            l3=F.Convolution2D(64, 64, ksize=3, stride=1, nobias=False, wscale=np.sqrt(2)),
            l4=F.Linear(3136, 512, wscale=np.sqrt(2)),
            out=F.Linear(512, self.n_action, initialW=np.zeros((n_action, 512), dtype=np.float32))
        )
        if on_gpu:
            self.to_gpu()