(Completed Nim as part of the tic tac toe lab.)

What I changed
(I made a copy of game_stub.py called game.py and corrected the methods
so that the game would work.)

Why I changed it
(To complete the lab.)

Estimate for remaining time to finish assignment: [Done]

nim/game.py

@@ -0,0 +1,49 @@
+class NimGame:
+    """A Nim game class based off NimGameStub.
+    """
+    def get_initial_state(self):
+        ''' Constructs the game board and has player 1 start the game. '''
+        return {
+            "board": [1, 3, 5, 7],
+            "first_player": True
+        }
+
+    def get_next_state(self, state, action):
+        ''' Creates a copy of the current board and then makes adjustments
+        based on the chosen action from a player's turn. '''
+        new_board = state["board"].copy()
+        new_board[action[0]] = new_board[action[0]] - action[1]
+        return {
+            "board": new_board,
+            "first_player": not state["first_player"],
+        }
+    
+    def get_actions(self, state):
+        ''' Construct the list of actions that can be taken by a player.
+        Is there a more efficient way of doign this? '''
+        actions = []
+        new_board = state["board"].copy()
+        for i in range(4):                      # check the four rows of the board
+            if new_board[i] > 0:                # if a row is not empty
+                for j in range(1,4):            # check if you can remove 1, 2, or 3 ticks in the row
+                    if j <= new_board[i]:       # if so
+                        actions.append((i,j))   # include that as an option
+        return actions   
+
+    def get_reward(self, state):
+        ''' Reports who wins. '''
+        if state["first_player"]:
+            return 1    # If it is the player's turn and there is nothing on the board, then it was the robot who crossed off the last line.
+        return 0        # Otherwise, the first player made the last move and lost.
+
+    def is_over(self, state):
+        ''' Reports true if there are no more lines to cross. '''
+        if all(ticks == 0 for ticks in state["board"]):
+            return True
+        return False
+
+    def get_objective(self, state):
+        ''' Reports the desired obejctive to help choose the move that 
+        yields the optimal reward under the lookahead_strategy for
+        computer players. '''
+        return max if state["first_player"] else min

nim/player.py

@@ -1,16 +1,16 @@
-from nim.game_stub import NimGameStub
+from nim.game import NimGame
 from strategy.lookahead_strategy import LookaheadStrategy
 
 class HumanNimPlayer:
     def __init__(self, name):
         self.name = name
-        self.game = NimGameStub()
+        self.game = NimGame()
 
     def choose_action(self, state):
         actions = self.game.get_actions(state)
         for i, action in enumerate(actions):
             row, lines_to_remove = action
-            print(f"{i}. Remove {lines_to_remove} from row {row}.")
+            print(f"{i}. Remove {lines_to_remove} from row {row+1}.")
         choice = self.get_int(len(actions))
         return actions[choice]
 
@@ -26,10 +26,10 @@ class HumanNimPlayer:
 class ComputerNimPlayer:
     def __init__(self, name):
         self.name = name
-        self.strategy = LookaheadStrategy(NimGameStub(), max_depth=3, deterministic=False)
+        self.strategy = LookaheadStrategy(NimGame(), max_depth=5, deterministic=False)
 
     def choose_action(self, state):
         action = self.strategy.choose_action(state)
         row, lines_to_remove = action
-        print(f"{self.name} removes {lines_to_remove} from row {row}")
+        print(f"{self.name} removes {lines_to_remove} from row {row+1}")
         return action

nim/view.py

@@ -1,9 +1,9 @@
-from nim.game_stub import NimGameStub
+from nim.game import NimGame
 
 class NimView:
     def __init__(self, player0, player1):
         self.players = [player0, player1]
-        self.game = NimGameStub()
+        self.game = NimGame()
 
     def greet(self):
         print(f"{self.players[0].name} and {self.players[1].name}, welcome to Nim.")

notes.md

@@ -37,4 +37,5 @@ For the first one, I would put an X on the rightmost cell in the middle row. Thi
 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? 
 
+The current and future reward for this state is 1. This means the state favors player X assuming both players continue using the same look ahead strategy.
 

play_nim.py

@@ -1,11 +1,11 @@
-from nim.game_stub import NimGameStub
+from nim.game import NimGame
 from nim.view import NimView
 from nim.player import HumanNimPlayer, ComputerNimPlayer
 
 player0 = HumanNimPlayer(input("What's your name? "))
 player1 = ComputerNimPlayer("Robot")
 view = NimView(player0, player1)
-game = NimGameStub()
+game = NimGame()
 
 view.greet()
 state = game.get_initial_state()

play_ttt.py

@@ -2,8 +2,8 @@ from ttt.game import TTTGame
 from ttt.view import TTTView
 from ttt.player import TTTHumanPlayer, TTTComputerPlayer
 
-player0 = TTTHumanPlayer("Player 1")
+player0 = TTTHumanPlayer("Pleayer 1")
-player1 = TTTHumanPlayer("Player 2")
+player1 = TTTComputerPlayer("Robot 1")
 game = TTTGame()
 view = TTTView(player0, player1)
 

ttt/player.py

@@ -1,4 +1,5 @@
 from click import Choice, prompt
+from strategy.lookahead_strategy import LookaheadStrategy
 from strategy.random_strategy import RandomStrategy
 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(),deterministic=False)
 
     def choose_action(self, state):
         "Chooses a random move from the moves available."