490f5b7364da85d414f4b8e93b3699e4d1b516f5,src/garage/tf/baselines/continuous_mlp_baseline.py,ContinuousMLPBaseline,fit,#ContinuousMLPBaseline#Any#,39

Before Change

        
        observations = np.concatenate([p["observations"] for p in paths])
        returns = np.concatenate([p["returns"] for p in paths])
        self._regressor.fit(observations, returns.reshape((-1, 1)))

    def predict(self, paths):
        Predict value based on paths.

After Change

        tabular.record("{}/LossBefore".format(self._name), loss_before)
        self._optimizer.optimize(inputs)
        loss_after = self._optimizer.loss(inputs)
        tabular.record("{}/LossAfter".format(self._name), loss_after)
        tabular.record("{}/dLoss".format(self._name), loss_before - loss_after)

    def predict(self, paths):

Instances