latent_regressor.py 文件源码

def predict_log_likelihood(self, paths, latents):
        if self.recurrent:
            observations = np.array([p["observations"][:, self.obs_regressed] for p in paths])
            actions = np.array([p["actions"][:, self.act_regressed] for p in paths])
            obs_actions = np.concatenate([observations, actions], axis=2)  # latents must match first 2dim: (batch,time)
        else:
            observations = np.concatenate([p["observations"][:, self.obs_regressed] for p in paths])
            actions = np.concatenate([p["actions"][:, self.act_regressed] for p in paths])
            obs_actions = np.concatenate([observations, actions], axis=1)
            latents = np.concatenate(latents, axis=0)
        if self.noisify_traj_coef:
            noise = np.random.multivariate_normal(mean=np.zeros_like(np.mean(obs_actions, axis=0)),
                                                         cov=np.diag(np.mean(np.abs(obs_actions),
                                                                     axis=0) * self.noisify_traj_coef),
                                                         size=np.shape(obs_actions)[0])
            obs_actions += noise
        if self.use_only_sign:
            obs_actions = np.sign(obs_actions)
        return self._regressor.predict_log_likelihood(obs_actions, latents)  # see difference with fit above...