Possible approach to implement the search strategy

search_strategy.py

def search_strategy():
    r""" Function to combine search space bits together 
    and create a new model"""
    
    # retrieve the output from search space 
    space_output = search_space()
    # from here use a suitable technique to retrieve new models 
    models = MonteCarloSearchTree(space_output)
    # alternatively we could build something like 
    model = Sequential() 
    for layers in space_output:
      model.add(layer)
      # add conditions on layers e.g. add a layer randomly
     
    return model