alpha_ and lambda_ are not necessary for contextual linear bandit algorithms

[Kurorororo]

Currently, contextual linear and logistic bandit algorithms share the same superclass BaseContextualPolicy.
The constructor of BaseContextualPolicy has alpha_ and lambda_ as arguments:

zr-obp/obp/policy/base.py

Lines 93 to 129 in c9ad20c

 @dataclass 
 class BaseContextualPolicy(metaclass=ABCMeta): 
     """Base class for contextual bandit policies. 
  
     Parameters 
     ---------- 
     dim: int 
         Number of dimensions of context vectors. 
  
     n_actions: int 
         Number of actions. 
  
     len_list: int, default=1 
         Length of a list of actions recommended in each impression. 
         When Open Bandit Dataset is used, 3 should be set. 
  
     batch_size: int, default=1 
         Number of samples used in a batch parameter update. 
  
     alpha_: float, default=1. 
         Prior parameter for the online logistic regression. 
  
     lambda_: float, default=1. 
         Regularization hyperparameter for the online logistic regression. 
  
     random_state: int, default=None 
         Controls the random seed in sampling actions. 
  
     """ 
  
     dim: int 
     n_actions: int 
     len_list: int = 1 
     batch_size: int = 1 
     alpha_: float = 1.0 
     lambda_: float = 1.0 
     random_state: Optional[int] = None 

These arguments are used to initialize self.alpha_list and self.lambda_list, which are used by LogisticEpsilonGreedy, LogisticTS, and LogisticUCB but not used by LinearEpsilonGreedy, LinTS, and LinUCB.
I suggest moving alpha_, lambda_, self.alpha_list, and self.lambda_list to another class, BaseLogisticPolicy for example, and making logistic policies inherit this new class.

[yuta-saito]

@Kurorororo Can you fix this issue by yourself after finishing #78 ?

[Kurorororo]

Sure!