db09dc1fb503ab8f7de69fa23e8d38742bda8e90,ch07/lib/dqn_model.py,NoisyFactorizedLinear,__init__,#NoisyFactorizedLinear#Any#Any#Any#Any#,40

Before Change

    def __init__(self, in_features, out_features, sigma_zero=0.4, bias=True):
        super(NoisyFactorizedLinear, self).__init__(in_features, out_features, bias=bias)
        sigma_init = sigma_zero / math.sqrt(in_features)
        self.sigma_weight = nn.Parameter(torch.Tensor(out_features, in_features).fill_(sigma_init))
        self.register_buffer("epsilon_input", torch.zeros(1, in_features))
        self.register_buffer("epsilon_output", torch.zeros(out_features, 1))
        if bias:
            self.sigma_bias = nn.Parameter(torch.Tensor(out_features).fill_(sigma_init))

    def forward(self, input):
        torch.randn(self.epsilon_input.size(), out=self.epsilon_input)

After Change

    
    def __init__(self, in_features, out_features, sigma_zero=0.4, bias=True):
        super(NoisyFactorizedLinear, self).__init__(in_features, out_features, bias=bias)
        sigma_init = sigma_zero / math.sqrt(in_features)
        self.sigma_weight = nn.Parameter(torch.full((out_features, in_features), sigma_init))
        self.register_buffer("epsilon_input", torch.zeros(1, in_features))
        self.register_buffer("epsilon_output", torch.zeros(out_features, 1))
        if bias:
            self.sigma_bias = nn.Parameter(torch.full((out_features,), sigma_init))

    def forward(self, input):
        self.epsison_input.normal_()

Instances