My neural network for actor critic financial trading

Policy.py

class Policy(nn.Module):
    def __init__(self):
        super(Policy, self).__init__()
        self.input_layer = nn.Linear(8, 128)
        self.hidden_1 = nn.Linear(128, 128)
        self.hidden_2 = nn.Linear(32,31)
        self.hidden_state = torch.tensor(torch.zeros(2,1,32), requires_grad=False).cuda()
        self.rnn = nn.GRU(128, 32, 2)
        self.action_head = nn.Linear(31, 5)
        self.value_head = nn.Linear(31, 1)
        self.saved_actions = []
        self.rewards = []

    def reset_hidden(self):
        self.hidden_state = torch.tensor(torch.zeros(2,1,32), requires_grad=False).cuda()
        
    def forward(self, x):
        x = torch.tensor(x).cuda()
        x = torch.sigmoid(self.input_layer(x))
        x = torch.tanh(self.hidden_1(x))
        x, self.hidden_state = self.rnn(x.view(1,-1,128), self.hidden_state.data)
        x = F.relu(self.hidden_2(x.squeeze()))
        action_scores = self.action_head(x)
        state_values = self.value_head(x)
        return F.softmax(action_scores, dim=-1), state_values