reinforce_continuous.py 文件源码

def select_action(self, state):
        mu, sigma_sq = self.model(Variable(state).cuda())
        sigma_sq = F.softplus(sigma_sq)

        eps = torch.randn(mu.size())
        # calculate the probability
        action = (mu + sigma_sq.sqrt()*Variable(eps).cuda()).data
        prob = normal(action, mu, sigma_sq)
        entropy = -0.5*((sigma_sq+2*pi.expand_as(sigma_sq)).log()+1)

        log_prob = prob.log()
        return action, log_prob, entropy