def getSuccessors( self, state ): """ For a given state, this should return a list of triples, (successor, action, stepCost), where 'successor' is a successor to the current state, 'action' is the action required to get there, and 'stepCost' is the incremental cost of expanding to that successor """ utils.raiseNotDefined()
def retrieve(input): #Use your trained hopfield network to retrieve and return a pattern based on the #input pattern. #HopfieldNotes.pdf on canvas is a good reference for asynchronous updating which #has generally better convergence properties than synchronous updating. # pattern = inputPattern # num_iterate = len(inputPattern)*len(inputPattern) # for _ in range(num_iterate) : # np.random.shuffle(v_in) # step = 0 # for index in v_in: # if np.dot(self.h[index], pattern) < 0: # if pattern[index] == 1: # step += 1 # pattern[index] = 0 # else : # if pattern[index] == 0: # step += 1 # pattern[index] = 1 # if step == 0: # return pattern # return None print("TODO") utils.raiseNotDefined()
def addExperience(self, experience): """ Called by environment after observing a transition and reward experience should be in some format like (state, action, reward) """ utils.raiseNotDefined("addExperience")
def getAction( self, gameState ): """ Returns the minimax action from the current gameState using self.depth and self.evaluationFunction. """ " *** YOUR CODE HERE ***" utils.raiseNotDefined()
def classify(inputPattern): #Classify should consider the input and classify as either, five or two #You will call your retrieve function passing the input #Compare the returned pattern to the 'perfect' instances #return a string classification 'five', 'two' or 'unknown' print("TODO") utils.raiseNotDefined()
def betterEvaluationFunction( currentGameState ): """ Your extreme ghost-hunting, pellet-nabbing, food-gobbling, unstoppable evaluation function. """ " *** YOUR CODE HERE ***" utils.raiseNotDefined()
def getDistribution(self, state): "Returns a Counter encoding a distribution over actions from the provided state." utils.raiseNotDefined()
def EndGame(self,game_state,scores): utils.raiseNotDefined() pass
def TimeOutWarning(self,runner,id): utils.raiseNotDefined() pass
def getGoalState( self ): """ Returns the goal state for the search problem """ utils.raiseNotDefined()
def GetLegalMoves(self, state, moves): utils.raiseNotDefined()
def final(self, state): """ Called by environment at the end """ utils.raiseNotDefined("final")
def startEpisode(self): """ Called by environment when new episode is starting """ utils.raiseNotDefined("startEpisode")
def initialGameState(self): utils.raiseNotDefined() return 0
def isGoalState( self, state ): """ Returns True if and only if the state is a valid goal state """ utils.raiseNotDefined()
def distort_input(instance, percent_distortion): #percent distortion should be a float from 0-1 #Should return a distorted version of the instance, relative to distoriton Rate print("TODO") utils.raiseNotDefined()
def getAction(self, state): """ The Agent will receive a GameState and must return an action """ utils.raiseNotDefined("getAction")
def generateSuccessor(self, game_state, action, agent_id): utils.raiseNotDefined() return 0
def getCostOfActions( self, actions ): """ This method returns the total cost of a particular sequence of actions. The sequence must be composed of legal moves """ utils.raiseNotDefined()
def stopEpisode(self): """ Called by environment when episode is done """ utils.raiseNotDefined("stopEpisode")
def getLegalActions(self, game_state, agent_id): utils.raiseNotDefined() return []
def calScore(self, game_state,agent_id): utils.raiseNotDefined() return 0
def gameEnds(self): utils.raiseNotDefined() return False
def getAction(self, state, board): """ The Agent will receive a GameState (scotlandyard.py) and must return an action from one of the valid actions """ utils.raiseNotDefined()
def ExcuteAction(self,i,move,game_state): utils.raiseNotDefined() pass
def visualizeWeight(): #You can change these parameters if you need to utils.raiseNotDefined()
def getStartState( self ): """ Returns the start state for the search problem """ utils.raiseNotDefined()