Memory_size and memory_counter in DeepQNetwork

Question

what are the memory_size and the memory_counter in the DeepQNetwork:

class DeepQNetwork:
def __init__(
        self,
        n_actions,
        n_features,
        learning_rate=0.01,              
        reward_decay=0.9,
        e_greedy=0.9,                     
        replace_target_iter=300,          
        memory_size=500,                  
        batch_size=32,                    
        e_greedy_increment=None,
        output_graph=True,
        memory_counter=48    
):

Answer 1

memory_size is stored memory of all experiences and memory_counter is a random small batch of memory that is used to learn. Ps: look at the code line 144