Ensembles, in its different flavors (bagging, random decision forests and boosting) are groups of Decision Trees that predict together and issue a composed answer. They are usually preferred to Decision Trees because they provide more variance and solve problems like over-fitting. However, they are more complex an difficult to interpret.
To learn about all the available Ensembles configuration options using BigML's Dashboard, you can check the corresponding section of the Ensembles documentation. Also the Ensembles API documentation contains the information about the attributes that need to be specified to configure your source programmatically.