snn_mlp_policy.py 文件源码

def dist_info_sym(self, obs_var, latent_var=None):  # this is ment to be for one path!
        # now this is not doing anything! And for computing the dist_info_vars of npo_snn_rewardMI it doesn't work
        if latent_var is None:
            latent_var1 = theano.shared(np.expand_dims(self.latent_fix, axis=0))  # new fix to avoid putting the latent as an input: just take the one fixed!
            latent_var = TT.tile(latent_var1, [obs_var.shape[0], 1])

        # generate the generalized input (append latents to obs.)
        if self.bilinear_integration:
            extended_obs_var = TT.concatenate([obs_var, latent_var,
                                               TT.flatten(obs_var[:, :, np.newaxis] * latent_var[:, np.newaxis, :],
                                                          outdim=2)]
                                              , axis=1)
        else:
            extended_obs_var = TT.concatenate([obs_var, latent_var], axis=1)
        mean_var, log_std_var = L.get_output([self._l_mean, self._l_log_std], extended_obs_var)
        if self.min_std is not None:
            log_std_var = TT.maximum(log_std_var, np.log(self.min_std))
        return dict(mean=mean_var, log_std=log_std_var)