class Actor(nn.Module):
def __init__(self, input_size, hidden_size, output_size):
super(Actor, self).__init__()
self.linear1 = nn.Linear(input_size, hidden_size)
self.linear2 = nn.Linear(hidden_size, hidden_size)
self.linear3 = nn.Linear(hidden_size, output_size)
def forward(self, s):
x = F.relu(self.linear1(s))
x = F.relu(self.linear2(x))
x = torch.relu(self.linear3(x))
return x
最后需要一层softmax函数映射到01之间。