small changes

.gitignore

@@ -1 +1 @@
-/__pycache__/
+__pycache__/

GenTunic/gen_tuning.py

@@ -21,8 +21,10 @@ def gen_tuning_main(AMOUNT_TRIES, AMOUNT_RUNS, REWARD_ON_WIN, REWARD_ON_LOSE):
 
     best_fintess_values = []
     best_fitness = 0
+    counter = 0
 
     while True:
+        print(f"Starting eveloution round {counter + 1}")
         #? Calc fitness
         population_propability, fintess_values = calc_population_fitness(population, AMOUNT_TRIES, AMOUNT_RUNS, REWARD_ON_WIN, REWARD_ON_LOSE)
 
@@ -46,6 +48,8 @@ def gen_tuning_main(AMOUNT_TRIES, AMOUNT_RUNS, REWARD_ON_WIN, REWARD_ON_LOSE):
         #? Mutation
         population = mutation(new_population, MUTATION_RATE, GEN_SIZE)
 
+        counter += 1
+
 
     population_propability, fintess_values = calc_population_fitness(population, AMOUNT_TRIES, AMOUNT_RUNS, REWARD_ON_WIN, REWARD_ON_LOSE)
     best_fintess_index, best_fitness = fintess_values

GenTunic/gen_util.py

@@ -19,7 +19,7 @@ def create_population(size, GEN_SIZE):
 def calc_population_fitness(population_propability, AMOUNT_TRIES, AMOUNT_RUNS, REWARD_ON_WIN, REWARD_ON_LOSE):
     population_fitness_sum = 0
 
-    for individual in population_propability:
+    for i, individual in enumerate(population_propability):
         gen = individual["population"]
         alpha, epsilon, gamma = [project_bit(x) for x in np.split(gen, 3)]
         _, multiple_tries_win_prob = multipleTries(alpha, epsilon, gamma, AMOUNT_TRIES, AMOUNT_RUNS, REWARD_ON_WIN, REWARD_ON_LOSE)
@@ -28,6 +28,8 @@ def calc_population_fitness(population_propability, AMOUNT_TRIES, AMOUNT_RUNS, R
         individual["probability"] = fitness
         population_fitness_sum += fitness
 
+        print(f"{i}: {fitness}")
+
 
     best_fitness_index = np.argmax(population_propability["probability"])
     best_fitness = population_propability[best_fitness_index]["probability"]

ReinforcmentLearning/learning.py

@@ -7,7 +7,6 @@ from ReinforcmentLearning.util import initial_q_fill
 
 
 
-
 def multipleTries(EPSILON, ALPHA, GAMMA, AMOUNT_TRIES, AMOUNT_RUNS, REWARD_ON_WIN, REWARD_ON_LOSE):
     cookies_per_try = []
     wins_per_try = []