sfja.skp/matchbox_tictactoe
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ais against each other

Browse Source
This commit is contained in:
Simon 2025-02-18 15:56:56 +01:00
parent 006997f9d5
commit d137e0149b
1 changed files with 42 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
main.py
View File

@ -96,9 +96,8 @@ class Board:
print("#############") print("#############")
START_WEIGHT = 20 START_WEIGHT = 20
WIN_REWARD = 3 WIN_REWARD = 1
DRAW_REWARD = 0 PUNUSHMENT = 1
PUNUSHMENT = 2
class AiPlayer: class AiPlayer:
def __init__(self, ch: Ch) -> None: def __init__(self, ch: Ch) -> None:
@ -113,10 +112,6 @@ class AiPlayer:
for choice in self.current_choices: for choice in self.current_choices:
self.choices[choice] += WIN_REWARD self.choices[choice] += WIN_REWARD
def reward_draw(self):
for choice in self.current_choices:
self.choices[choice] += DRAW_REWARD
def punish_loss(self): def punish_loss(self):
for choice in self.current_choices: for choice in self.current_choices:
self.choices[choice] -= PUNUSHMENT self.choices[choice] -= PUNUSHMENT
@ -141,7 +136,7 @@ class AiPlayer:
for idx, choice in possible_choices: for idx, choice in possible_choices:
choice = self.interned_choice(choice) choice = self.interned_choice(choice)
key = choice.key() key = choice.key()
if not candiate_weigth or self.choices[key] > candiate_weigth: if not candiate_weigth or self.choices[key] > candiate_weigth + 4:
candiate_weigth = self.choices[key] candiate_weigth = self.choices[key]
candidate_idcs = [(idx, key)] candidate_idcs = [(idx, key)]
elif self.choices[key] == candiate_weigth: elif self.choices[key] == candiate_weigth:
@ -163,46 +158,67 @@ class AiPlayer:
for key in vs: for key in vs:
self.choices[int(key)] = vs[key] self.choices[int(key)] = vs[key]
class Game:
def __init__(self) -> None:
self.current_plays = []
self.weights = {}
def main(): def main():
p0 = AiPlayer(Ch.Cross) p1 = AiPlayer(Ch.Cross)
p2 = AiPlayer(Ch.Circle)
games = 0 games = 0
p1_wins = 0
p2_wins = 0
draws = 0
print("Training P1 against P2...")
for _ in range(1000):
board = Board()
p1.clear_choices()
p2.clear_choices()
while True:
p1.make_play(board)
if board.player_has_won(Ch.Cross):
p1_wins += 1
p1.reward_win()
p2.punish_loss()
break
if board.is_draw():
draws += 1
break
p2.make_play(board)
if board.player_has_won(Ch.Circle):
p2_wins += 1
p2.reward_win()
p1.punish_loss()
break
if board.is_draw():
break
games += 1
print(f"Games {games} Score: P1: {p1_wins}, P2: {p2_wins}, draws: {draws}")
while True: while True:
print(f"\n\nGame #{games}") print("\nNew game")
board = Board() board = Board()
p0.clear_choices() p1.clear_choices()
while True: while True:
print("AI's turn") print("AI's turn")
p0.make_play(board) p1.make_play(board)
board.print() board.print()
if board.player_has_won(Ch.Cross): if board.player_has_won(Ch.Cross):
print("AI won!") print("AI won!")
print("Rewarding AI...")
p0.reward_win()
break break
print("Your turn (0..8)") print("Your turn (0..8)")
if board.is_draw(): if board.is_draw():
print("Draw!") print("Draw!")
print("Rewarding AI...")
p0.reward_draw()
break break
possible_choices = board.possible_plays() possible_choices = board.possible_plays()
should_restart = False should_restart = False
while True: while True:
text = input("> ") text = input("> ")
if text == ".save": if text == ".save":
p0.save_to_file() p1.save_to_file()
continue continue
elif text == ".load": elif text == ".load":
p0.load_from_file() p1.load_from_file()
choice = 0 choice = 0
should_restart = True should_restart = True
break break
@ -223,11 +239,10 @@ def main():
board.print() board.print()
if board.player_has_won(Ch.Circle): if board.player_has_won(Ch.Circle):
print("Player won!") print("Player won!")
print("Punishing AI...")
p0.punish_loss()
break break
games += 1 games += 1
try: try:
main() main()
except KeyboardInterrupt: except KeyboardInterrupt: