The MAE (mean absolute error) is the mean of the absolute gaps, in the unit of the target. The RMSE is the square root of the mean of the squared errors, which penalizes large errors more. R² indicates the share of variance explained by the model; it is 1 for a perfect fit.
Example
mean_absolute_error(y_test, pred)
root_mean_squared_error(y_test, pred)