def runGame(p1, p2):
p1.resetForNewGame()
p2.resetForNewGame()
d1 = Dealer(5)
p1.cards = d1.dealCards()[0]
p2.cards = d1.dealCards()[0]
gameState = GameState(p1, p2)
aqlearnScore = 0
gameLoop = True
while gameLoop:
p1.pickCard()
p2.pickCard()
roundWinner = gameState.judgeRound(p1, p2)
#? generating successor
if roundWinner == p1:
p1.accumulatedCards[p1.playedCard[1]] += 1
if roundWinner == p2:
p2.accumulatedCards[p2.playedCard[1]] += 1
if gameState.judgeGameOver(p1, p2) == p1:
return p1.name
elif gameState.judgeGameOver(p1, p2) == p2:
return p2.name
p1.cards.append(d1.generateRandomCard())
p2.cards.append(d1.generateRandomCard())
def runGame(p1, p2, mute):
p1.resetForNewGame()
p2.resetForNewGame()
d1 = Dealer(5)
p1.cards = d1.dealCards()[0]
p2.cards = d1.dealCards()[0]
gameState = GameState(p1, p2)
aqlearnScore = 0
gameLoop = True
while gameLoop:
# print(bcolors.OKBLUE+"opponent cards:")
# for i, x in enumerate(p2.cards):
# print(" " + str(i + 1) + ". " + str(x))
# print(bcolors.ENDC)
#! aqlearn agent steps
#1. update
#2. get action
#3. generateSuccessor
# print("Your cards:")
# # print(p1.cards)
# for i, x in enumerate(p1.cards):
# print(" " + str(i + 1) + ". " + str(x))
# print("Enter the numerical value of the card you'd like to pick.")
# choice = int(input(">>> ")) - 1
# if choice >= len(p1.cards):
# print(bcolors.WARNING + "Invalid index! Try again..." + bcolors.ENDC)
# continue
p1.update(gameState, aqlearnScore)
action = p1.doAction(gameState)
p1.pickCard(action)
p2.pickCard()
#call agent.update()
#
roundWinner = gameState.judgeRound(p1, p2)
#? generating successor
if roundWinner == p1:
# if not mute:
# print(bcolors.OKGREEN + "APQ won that round!" + bcolors.ENDC)
p1.accumulatedCards[p1.playedCard[1]] += 1
if roundWinner == p2:
# if not mute:
# print(bcolors.FAIL + "APQ lost that round." + bcolors.ENDC)
p2.accumulatedCards[p2.playedCard[1]] += 1
#? get transitional rewards
p1TransitionalReward = gameState.getRewards(p1, p2)
aqlearnScore += p1TransitionalReward
# print(bcolors.OKGREEN + "TransitionalRewards:", str(p1TransitionalReward) + bcolors.ENDC )
# print(bcolors.OKGREEN + "Total Score:", str(aqlearnScore) + bcolors.ENDC )
# print(" Score ")
# print("***************************")
# print(p1.name + ": ")
# print("Fire: " + str(p1.accumulatedCards["Fire"]))
# print("Water: " + str(p1.accumulatedCards["Water"]))
# print("Ice: " + str(p1.accumulatedCards["Ice"]))
# print(p2.name + ": ")
# print("Fire: " + str(p2.accumulatedCards["Fire"]))
# print("Water: " + str(p2.accumulatedCards["Water"]))
# print("Ice: " + str(p2.accumulatedCards["Ice"]))
# print("")
if gameState.judgeGameOver(p1, p2) == p1:
p1.update(gameState, aqlearnScore)
if not mute:
print(bcolors.OKBLUE + "Game Over!", p1.name + " wins!" + bcolors.ENDC)
p1.printEpisodeInfo()
return (aqlearnScore, "aql")
elif gameState.judgeGameOver(p1, p2) == p2:
p1.update(gameState, aqlearnScore)
if not mute:
print(bcolors.FAIL + "Game Over!", p2.name + " wins!" + bcolors.ENDC)
p1.printEpisodeInfo()
return (aqlearnScore, "greedy")
p1.cards.append(d1.generateRandomCard())
p2.cards.append(d1.generateRandomCard())