From c2ae97588ab13026d87b3f8f969f2968caebe3fc Mon Sep 17 00:00:00 2001
From: Thomas Naber <tom@Thomass-MacBook-Air.local>
Date: Sun, 25 Feb 2024 21:52:47 -0500
Subject: [PATCH] Checkpoint 3

What I changed
I changed the computer to use the lookahead strategy rather than the random picker strategy.

Why I changed it
It's boring to play agains the computer when all it does is pick a random available spot. When the computer
plays intelligently it's more interesting and difficult.

Estimate for remaining time to finish assignment: [30 minutes to an hour]
---
 .DS_Store     | Bin 0 -> 6148 bytes
 notes.md      |  16 ++++++++++------
 play_ttt.py   |   4 ++--
 ttt/player.py |   3 ++-
 4 files changed, 14 insertions(+), 9 deletions(-)
 create mode 100644 .DS_Store

diff --git a/.DS_Store b/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..83848f4e989a24b110674a179ac85b8aebecbcf0
GIT binary patch
literal 6148
zcmeHKOHRWu5Pj2j5mX6v$p$GWsKgCIRTiv!0O(H@C2gt_kh;sBJ8%Wg#|qxqR)yWd
z3L$}Jr16XGd7k)Lv10%-c${4TJpdV9v30`Yh-tt2fwe-5@<hj|rjxRou%^SA{RIVd
z?b=x54y)@jTE9#7^xvJiiDZnbP-Bh<^s&M$iGNMvyV#(_7(3kf@yXg?7qjI28&=J1
z^-<RI5mv=FtFdLiKJ!+X;y%gsmatCsedt?8FUg*|Y&B~ulrgupNVpkQ&}?Itb1c$%
zLDhSS)Jx)@M%#5+t#w>}J6r=d+c+y!)6b)@YGw+U0;a$ZD4_ceE$e!;(iAWSOo6=u
zx<BM}#Ufzi(QO?p+!cV>VY4$nyPtnzt_{Q@VB?W3H1SlTr%JeDNVq$Qr?bBZ@r_4M
zhq%lfCuEjzLy>Uxklcks3XfKr0;WK$K-*V)dj4O1egBV1Rx<@mfq$idbcUnhfKv)*
y>%rvotj+1SbTy4@Jnkuca7Qs?^(a20J7asU55yv1<B=^i`w?(5SYZnMssbOVfPgdr

literal 0
HcmV?d00001

diff --git a/notes.md b/notes.md
index 72b3a73..cef50b3 100644
--- a/notes.md
+++ b/notes.md
@@ -21,20 +21,24 @@ an array that I'm accessing, and that indexes 0 through 9 correspond to the diff
 board starting on the top left and going across the row, then down to the left of the next row, etc.
 What I do not understand is what state is and why we need to use state["board"][index] to access 
 something on the boare
-### TTT Strategy
 
+### TTT Strategy
 For each of the following board states, if you are playing as X
 and it's your turn, which action would you take? Why?
 
-   | O | O       |   | O       | X |       X | O |   
+ 0 | O | O     0 | 1 | O     0 | X | 2     X | O | 2 
 ---+---+---   ---+---+---   ---+---+---   ---+---+---
- X | X |         | X |       X | O | O       |   |   
+ X | X | 5     3 | X | 5     X | O | O     3 | 4 | 5 
 ---+---+---   ---+---+---   ---+---+---   ---+---+---
-   |   |         |   | O       |   |         |   |   
+ 6 | 7 | 8     6 | 7 | O     6 | 7 | 8     6 | 7 | 8 
+
+1 - You should play in space 5, since you'll win the game.
+2 - You should play in space 5 since that will block the O player from winning and also give you two in a row.
+3 - You should play in space 0, since that will give you two chances to win on your next move and the other player can only block one of them. 
+4 - Play in space 4. This blocks the other player from using the O they placed. 
 
 ### Initial game state
-
 You can get the inital game state using game.get_initial_state(). 
 What is the current and future reward for this state? What does this mean? 
-
+I think the current reward is 1, meaning x wins, and the future reward is 0. This means that at the beginning of the game, x who is the first player is likely to win, but after the computer tests all of it's cases, it's likely that the game will end in a draw. This makes sense to me. It wasn't too difficult to tie with the computer, however it was difficult to beat the computer. 
 
diff --git a/play_ttt.py b/play_ttt.py
index ef5530a..bbb9246 100644
--- a/play_ttt.py
+++ b/play_ttt.py
@@ -3,7 +3,7 @@ from ttt.view import TTTView
 from ttt.player import TTTHumanPlayer, TTTComputerPlayer
 
 player0 = TTTHumanPlayer("Player 1")
-player1 = TTTHumanPlayer("Player 2")
+player1 = TTTComputerPlayer("Player 2")
 game = TTTGame()
 view = TTTView(player0, player1)
 
@@ -12,4 +12,4 @@ view.greet()
 while not game.is_over(state):
     action = view.get_action(state)
     state = game.get_next_state(state, action)
-view.conclude(state)
+view.conclude(state)
\ No newline at end of file
diff --git a/ttt/player.py b/ttt/player.py
index bfbbe15..9939743 100644
--- a/ttt/player.py
+++ b/ttt/player.py
@@ -1,5 +1,6 @@
 from click import Choice, prompt
 from strategy.random_strategy import RandomStrategy
+from strategy.lookahead_strategy import LookaheadStrategy
 from ttt.game import TTTGame
 import random
 
@@ -24,7 +25,7 @@ class TTTComputerPlayer:
     def __init__(self, name):
         "Sets up the player."
         self.name = name
-        self.strategy = RandomStrategy(TTTGame())
+        self.strategy = LookaheadStrategy(TTTGame())
 
     def choose_action(self, state):
         "Chooses a random move from the moves available."