Yao-Yuan Yang

This algorithm is originally not designed for delayed reward.

It should be this one https://github.com/ntucllab/libact/blob/master/libact/query_strategies/active_learning_by_learning.py#L337

We haven't officially support batch mode active learning yet. Though some algorithms with slight modification can achieve this feature. Take uncertainty sampling for example, you may change the following line...

You may want to check your environment variables like PYTHONPATH or PATH. Or maybe you are inside a virtualenv where you don't need sudo to install the package.

Do you mean that the feature is separated with the pixel array? If this is what you mean, I think you can try putting the corresponding pixel array to the...

The most simply way of doing it is to take featureX and search through [features1,...,featuresN] one by one for the index and then go back to the imageX. Though if...

Can you show more about how you install the package?

It appears there are errors building the variance_reduction query_strategy. If you are not using that algorithm, you can go with ``` LIBACT_BUILD_VARIANCE_REDUCTION =0 pip install git+https://github.com/ntucllab/libact.git ``` If you need...

Yes, if you have a linux environment, it should be easier to install.

#141