Open ssimonc opened 3 years ago
@ssimonc Sorry for the late reply. The model picking feature is not implemented yet. Currently, the main focus is reproducing the all model-free algorithms for paper publication. After this, we're gonna spend more time on the model-based algorithms. Sorry for the inconvenience.
Hi @takuseno, First of all, thanks for the great work.
I've a question regarding the MOPO algorithm, specifically about the ProbabilisticEnsembleDynamics.
In the original paper, authors state:
In order to reproduce the paper, starting from your example in the doc:
For the models, I can assume that it is simply necessary to provide an appropriate encoder_factory, instead of using the default one
However, with respect to the ensemble, Is there a particular reason why you decided to implement it without the 'pick the best k models out of N models' step (e.g. train 5 models and use all of them instead of taking the best 5 out of 7)?
Am I missing something or can this be a feature to work on?