Spaces:
Sleeping
Sleeping
Commit
Β·
6ac8ae0
1
Parent(s):
849fda6
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import numpy as np
|
3 |
+
from objects import Player, HumanPlayer, State
|
4 |
+
import random
|
5 |
+
# Create RL bot players
|
6 |
+
p1 = Player("p1")
|
7 |
+
p2 = HumanPlayer("p2")
|
8 |
+
|
9 |
+
# Initialize the selected opponent in Session State
|
10 |
+
if "selected_opponent" not in st.session_state:
|
11 |
+
st.session_state.selected_opponent = 'Computer'
|
12 |
+
|
13 |
+
def handle_click(i, j):
|
14 |
+
if (i, j) not in check_available_moves(extra=True):
|
15 |
+
st.session_state.warning = True
|
16 |
+
elif not st.session_state.winner:
|
17 |
+
st.session_state.warning = False
|
18 |
+
st.session_state.board[i, j] = st.session_state.player
|
19 |
+
st.session_state.player = "O" if st.session_state.player == "X" else "X"
|
20 |
+
winner = check_win(st.session_state.board)
|
21 |
+
if winner != ".":
|
22 |
+
st.session_state.winner = winner
|
23 |
+
if st.session_state.opponent == 'Computer':
|
24 |
+
# Give reward to the RL bot and update its policy
|
25 |
+
if winner == 'X':
|
26 |
+
p1.feedReward(1)
|
27 |
+
elif winner == 'O':
|
28 |
+
p1.feedReward(0)
|
29 |
+
else:
|
30 |
+
p1.feedReward(0.1)
|
31 |
+
|
32 |
+
# Save the RL bot's policy
|
33 |
+
p1.savePolicy()
|
34 |
+
|
35 |
+
|
36 |
+
def init(post_init=False):
|
37 |
+
if not post_init:
|
38 |
+
st.session_state.opponent = 'Human'
|
39 |
+
st.session_state.win = {'X': 0, 'O': 0}
|
40 |
+
st.session_state.board = np.full((3, 3), '.', dtype=str)
|
41 |
+
st.session_state.player = 'X'
|
42 |
+
st.session_state.warning = False
|
43 |
+
st.session_state.winner = None
|
44 |
+
st.session_state.over = False
|
45 |
+
|
46 |
+
def check_available_moves(extra=False) -> list:
|
47 |
+
raw_moves = [row for col in st.session_state.board.tolist() for row in col]
|
48 |
+
num_moves = [i for i, spot in enumerate(raw_moves) if spot == '.']
|
49 |
+
if extra:
|
50 |
+
return [(i // 3, i % 3) for i in num_moves]
|
51 |
+
return num_moves
|
52 |
+
|
53 |
+
def check_rows(board):
|
54 |
+
for row in board:
|
55 |
+
if len(set(row)) == 1:
|
56 |
+
return row[0]
|
57 |
+
return None
|
58 |
+
|
59 |
+
def check_diagonals(board):
|
60 |
+
if len(set([board[i][i] for i in range(len(board))])) == 1:
|
61 |
+
return board[0][0]
|
62 |
+
if len(set([board[i][len(board) - i - 1] for i in range(len(board))])) == 1:
|
63 |
+
return board[0][len(board) - 1]
|
64 |
+
return None
|
65 |
+
|
66 |
+
def check_state():
|
67 |
+
if st.session_state.winner:
|
68 |
+
st.success(f"Congrats! {st.session_state.winner} won the game! π")
|
69 |
+
if st.session_state.warning and not st.session_state.over:
|
70 |
+
st.warning('β οΈ This move already exists')
|
71 |
+
if st.session_state.winner and not st.session_state.over:
|
72 |
+
st.session_state.over = True
|
73 |
+
st.session_state.win[st.session_state.winner] = (
|
74 |
+
st.session_state.win.get(st.session_state.winner, 0) + 1
|
75 |
+
)
|
76 |
+
elif not check_available_moves() and not st.session_state.winner:
|
77 |
+
st.info(f"It's a tie π")
|
78 |
+
st.session_state.over = True
|
79 |
+
|
80 |
+
def check_win(board):
|
81 |
+
for new_board in [board, np.transpose(board)]:
|
82 |
+
result = check_rows(new_board)
|
83 |
+
if result:
|
84 |
+
return result
|
85 |
+
return check_diagonals(board)
|
86 |
+
|
87 |
+
|
88 |
+
def computer_player():
|
89 |
+
moves = check_available_moves(extra=True)
|
90 |
+
if moves:
|
91 |
+
# Use p1 to choose the action
|
92 |
+
positions = check_available_moves(extra=True)
|
93 |
+
p1_action = p1.chooseAction(positions, st.session_state.board, -1)
|
94 |
+
|
95 |
+
# Check if the chosen action is valid and make the move
|
96 |
+
if p1_action in moves:
|
97 |
+
i, j = p1_action
|
98 |
+
handle_click(i, j)
|
99 |
+
|
100 |
+
|
101 |
+
def on_opponent_selected():
|
102 |
+
st.session_state.selected_opponent = st.session_state.opponent
|
103 |
+
init(True)
|
104 |
+
|
105 |
+
|
106 |
+
def main():
|
107 |
+
st.write(
|
108 |
+
"""
|
109 |
+
# βπ
ΎοΈ Tic Tac Toe
|
110 |
+
"""
|
111 |
+
)
|
112 |
+
|
113 |
+
if "board" not in st.session_state:
|
114 |
+
init()
|
115 |
+
|
116 |
+
reset, score, player, settings = st.columns([0.5, 0.6, 1, 1])
|
117 |
+
reset.button('New game', on_click=init, args=(True,))
|
118 |
+
|
119 |
+
# Dynamically set the Expander label based on the selected opponent
|
120 |
+
with settings.expander(f'Opponent ({st.session_state.selected_opponent})'):
|
121 |
+
st.write('**Warning**: changing this setting will restart your game')
|
122 |
+
st.selectbox(
|
123 |
+
'Set opponent',
|
124 |
+
['Computer','Human'],
|
125 |
+
key='opponent',
|
126 |
+
on_change=on_opponent_selected,
|
127 |
+
)
|
128 |
+
|
129 |
+
for i, row in enumerate(st.session_state.board):
|
130 |
+
cols = st.columns([5, 1, 1, 1, 5])
|
131 |
+
for j, field in enumerate(row):
|
132 |
+
cols[j + 1].button(
|
133 |
+
field,
|
134 |
+
key=f"{i}-{j}",
|
135 |
+
on_click=handle_click
|
136 |
+
if st.session_state.player == 'X'
|
137 |
+
or st.session_state.opponent == 'Human'
|
138 |
+
else computer_player(),
|
139 |
+
args=(i, j),
|
140 |
+
)
|
141 |
+
|
142 |
+
check_state()
|
143 |
+
|
144 |
+
score.button(f'β{st.session_state.win["X"]} π {st.session_state.win["O"]}β')
|
145 |
+
player.button(
|
146 |
+
f'{"β" if st.session_state.player == "X" else "β"}\'s turn'
|
147 |
+
if not st.session_state.winner
|
148 |
+
else f'π Game finished'
|
149 |
+
)
|
150 |
+
|
151 |
+
if __name__ == '__main__':
|
152 |
+
main()
|