3013050
/
MLE-Pacman
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

small changes

main
2wenty1ne 2025-12-03 16:07:25 +01:00
parent 738b122f43
commit d13e22c66e
4 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

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

4
GenTunic/gen_tuning.py
View File

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

4
GenTunic/gen_util.py
View File

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

1
ReinforcmentLearning/learning.py
View File

@ -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): def multipleTries(EPSILON, ALPHA, GAMMA, AMOUNT_TRIES, AMOUNT_RUNS, REWARD_ON_WIN, REWARD_ON_LOSE):
cookies_per_try = [] cookies_per_try = []
wins_per_try = [] wins_per_try = []