def getUserAction(state, actionFunction):
"""
Get an action from the user (rather than the agent).
Used for debugging and lecture demos.
"""
import graphicsUtils
action = None
while True:
keys = graphicsUtils.wait_for_keys()
if 'Up' in keys:
action = 'north'
if 'Down' in keys:
action = 'south'
if 'Left' in keys:
action = 'west'
if 'Right' in keys:
action = 'east'
if 'q' in keys:
sys.exit(0)
if action is None:
continue
break
actions = actionFunction(state)
if action not in actions:
action = actions[0]
return action
def getUserAction(state, actionFunction):
"""
Get an action from the user (rather than the agent).
Used for debugging and lecture demos.
"""
import graphicsUtils
action = None
while True:
keys = graphicsUtils.wait_for_keys()
if "Up" in keys:
action = "north"
if "Down" in keys:
action = "south"
if "Left" in keys:
action = "west"
if "Right" in keys:
action = "east"
if "q" in keys:
sys.exit(0)
if action == None:
continue
break
actions = actionFunction(state)
if action not in actions:
action = actions[0]
return action
def getUserAction(state, actionFunction):
"""
Get an action from the user (rather than the agent).
Used for debugging and lecture demos.
"""
import graphicsUtils
action = None
while True:
keys = graphicsUtils.wait_for_keys()
if "Up" in keys:
action = "north"
if "Down" in keys:
action = "south"
if "Left" in keys:
action = "west"
if "Right" in keys:
action = "east"
if "q" in keys:
sys.exit(0)
if action == None:
continue
break
actions = actionFunction(state)
if action not in actions:
action = actions[0]
return action
def getAction(self, state):
from graphicsUtils import wait_for_keys
legal = state.getLegalActions(self.index)
stateRepresentation = getStateRepresentation(state)
print "State Representation:", stateRepresentation
move = None
while move == None:
self.keys = wait_for_keys()
move = self.getMove(legal)
if move == None:
print "Illegal move. Try again"
actionRepresentation = getActionRepresentation(move)
print "Action Representation:", actionRepresentation
self.saveTraining([stateRepresentation, actionRepresentation])
return move
def getAction( self, state): from graphicsUtils import wait_for_keys legal = state.getLegalActions(self.index) stateRepresentation = getStateRepresentation(state) #print "State Representation:", stateRepresentation move = None while move == None: self.keys = wait_for_keys() move = self.getMove(legal) if move == None: print "Illegal move. Try again" actionRepresentation = getActionRepresentation(move) #print "Action Representation:", actionRepresentation self.saveTraining([self.convertState(state, stateRepresentation), self.convertAction(state, actionRepresentation)]) return move
def animatePacman(self, pacman, prevPacman, image):
if self.frameTime < 0:
print('Press any key to step forward, "q" to play')
keys = gU.wait_for_keys()
if 'q' in keys:
self.frameTime = 0.1
if self.frameTime > 0.01 or self.frameTime < 0:
fx, fy = self.getPosition(prevPacman)
px, py = self.getPosition(pacman)
frames = 4.0
for i in range(1, int(frames) + 1):
pos = px * i / frames + fx * (frames - i) / frames, \
py * i / frames + fy * (frames - i) / frames
self.movePacman(pos, self.getDirection(pacman), image)
gU.refresh()
gU.sleep(abs(self.frameTime) / frames)
else:
self.movePacman(self.getPosition(pacman),
self.getDirection(pacman), image)
gU.refresh()
def getUserAction(state, actionFunction):
"""
Get an action from the user (rather than the agent).
Used for debugging and lecture demos.
"""
import graphicsUtils
action = None
while True:
keys = graphicsUtils.wait_for_keys()
if 'Up' in keys: action = 'north'
if 'Down' in keys: action = 'south'
if 'Left' in keys: action = 'west'
if 'Right' in keys: action = 'east'
if 'q' in keys: sys.exit(0)
if action == None: continue
break
actions = actionFunction(state)
if action not in actions:
action = actions[0]
return action
def runGames(layout,
pacman,
ghosts,
display,
numGames,
record,
numTraining=0,
catchExceptions=False,
timeout=30,
keyboardGhosts=[],
savedDisplay=None):
import __main__
import time
__main__.__dict__['_display'] = display
rules = ClassicGameRules(timeout)
games = []
for i in range(numGames):
game = None
beQuiet = i < numTraining
if beQuiet:
# Suppress output and graphics
import textDisplay
gameDisplay = textDisplay.NullGraphics()
rules.quiet = True
if hasattr(display,
'showTrainingScreen') and display.showTrainingScreen:
display.initialize(None, "training")
else:
if savedDisplay is None:
gameDisplay = display
else:
gameDisplay = savedDisplay
rules.quiet = False
# If there's keyboard ghosts and not in training mode
if len(keyboardGhosts) > 0 and not beQuiet:
#for i in range(len(keyboardGhosts)):
# keyboardGhosts[i].init()
#ghostType = loadAgent("KeyboardGhost", False)
#keyboardGhosts = [ghostType( i+1 ) for i in range( len(keyboardGhosts) )]
game = rules.newGame(layout, pacman, keyboardGhosts, gameDisplay,
beQuiet, catchExceptions)
else:
game = rules.newGame(layout, pacman, ghosts, gameDisplay, beQuiet,
catchExceptions)
if beQuiet:
game.run()
else:
if savedDisplay is None:
savedDisplay = game.run()
savedDisplay = game.run()
else:
savedDisplay = game.run(savedDisplay)
if game.gameQuit:
return (games, display)
# Show win / loss message
if hasattr(display, 'showTrainingScreen'):
from graphicsUtils import wait_for_keys
display.showResultMessage(not game.state.isWin())
keys = []
if len(keyboardGhosts) > 0:
while 'Return' not in keys:
keys = wait_for_keys()
else:
time.sleep(1)
display.hideResultMessage()
if not beQuiet: games.append(game)
if record:
import time, cPickle
fname = ('recorded-game-%d' % (i + 1)) + '-'.join(
[str(t) for t in time.localtime()[1:6]])
f = file(fname, 'w')
components = {'layout': layout, 'actions': game.moveHistory}
cPickle.dump(components, f)
f.close()
if (numGames - numTraining) > 0:
scores = [game.state.getScore() for game in games]
wins = [game.state.isWin() for game in games]
progress = [
float(game.state.getNumFood()) / rules.initialState.getNumFood()
for game in games
]
winRate = wins.count(True) / float(len(wins))
print('Average Score:', sum(scores) / float(len(scores)))
print('Scores: ', ', '.join([str(score) for score in scores]))
print('Win Rate: %d/%d (%.2f)' %
(wins.count(True), len(wins), winRate))
print('Progress Rate: %.2f %%' %
((sum(progress) / len(progress)) * 100))
print('Record: ',
', '.join([['Loss', 'Win'][int(w)] for w in wins]))
return (games, display)
def runGames( layout, pacman, ghosts, display, numGames, record, numTraining = 0, catchExceptions=False, timeout=30, keyboardGhosts=[], savedDisplay=None ):
import __main__
import time
__main__.__dict__['_display'] = display
rules = ClassicGameRules(timeout)
games = []
for i in range( numGames ):
game = None
beQuiet = i < numTraining
if beQuiet:
# Suppress output and graphics
import textDisplay
gameDisplay = textDisplay.NullGraphics()
rules.quiet = True
if hasattr(display, 'showTrainingScreen') and display.showTrainingScreen:
display.initialize(None, "training")
else:
if savedDisplay is None:
gameDisplay = display
else:
gameDisplay = savedDisplay
rules.quiet = False
# If there's keyboard ghosts and not in training mode
if len(keyboardGhosts) > 0 and not beQuiet:
#for i in range(len(keyboardGhosts)):
# keyboardGhosts[i].init()
#ghostType = loadAgent("KeyboardGhost", False)
#keyboardGhosts = [ghostType( i+1 ) for i in range( len(keyboardGhosts) )]
game = rules.newGame( layout, pacman, keyboardGhosts, gameDisplay, beQuiet, catchExceptions)
else:
game = rules.newGame( layout, pacman, ghosts, gameDisplay, beQuiet, catchExceptions)
if beQuiet:
game.run()
else:
if savedDisplay is None:
savedDisplay = game.run()
else:
savedDisplay = game.run(savedDisplay)
if game.gameQuit:
return (games, display)
# Show win / loss message
if hasattr(display, 'showTrainingScreen'):
from graphicsUtils import wait_for_keys
display.showResultMessage(not game.state.isWin())
keys = []
if len(keyboardGhosts) > 0:
while 'Return' not in keys:
keys = wait_for_keys()
else:
time.sleep(1)
display.hideResultMessage()
if not beQuiet: games.append(game)
if record:
import time, cPickle
fname = ('recorded-game-%d' % (i + 1)) + '-'.join([str(t) for t in time.localtime()[1:6]])
f = file(fname, 'w')
components = {'layout': layout, 'actions': game.moveHistory}
cPickle.dump(components, f)
f.close()
if (numGames-numTraining) > 0:
scores = [game.state.getScore() for game in games]
wins = [game.state.isWin() for game in games]
progress = [float(game.state.getNumFood()) / rules.initialState.getNumFood() for game in games]
winRate = wins.count(True)/ float(len(wins))
print 'Average Score:', sum(scores) / float(len(scores))
print 'Scores: ', ', '.join([str(score) for score in scores])
print 'Win Rate: %d/%d (%.2f)' % (wins.count(True), len(wins), winRate)
print 'Progress Rate: %.2f %%' % ((sum(progress)/len(progress))*100)
print 'Record: ', ', '.join([ ['Loss', 'Win'][int(w)] for w in wins])
return (games, display)
