def forward()

in spinup/algos/pytorch/sac/core.py [0:0]

• 19 lines of code
• 8 McCabe index (conditional complexity)

    def forward(self, obs, deterministic=False, with_logprob=True):
        net_out = self.net(obs)
        mu = self.mu_layer(net_out)
        log_std = self.log_std_layer(net_out)
        log_std = torch.clamp(log_std, LOG_STD_MIN, LOG_STD_MAX)
        std = torch.exp(log_std)

        # Pre-squash distribution and sample
        pi_distribution = Normal(mu, std)
        if deterministic:
            # Only used for evaluating policy at test time.
            pi_action = mu
        else:
            pi_action = pi_distribution.rsample()

        if with_logprob:
            # Compute logprob from Gaussian, and then apply correction for Tanh squashing.
            # NOTE: The correction formula is a little bit magic. To get an understanding 
            # of where it comes from, check out the original SAC paper (arXiv 1801.01290) 
            # and look in appendix C. This is a more numerically-stable equivalent to Eq 21.
            # Try deriving it yourself as a (very difficult) exercise. :)
            logp_pi = pi_distribution.log_prob(pi_action).sum(axis=-1)
            logp_pi -= (2*(np.log(2) - pi_action - F.softplus(-2*pi_action))).sum(axis=1)
        else:
            logp_pi = None

        pi_action = torch.tanh(pi_action)
        pi_action = self.act_limit * pi_action

        return pi_action, logp_pi