def brute_force(max_steps):
best_action_num = 0
best_clean_cells = 0
actions = [1, 4, 4, 1, 2, 2, 2, 2]
agent = FakeMemorylessAgent(actions)
n = 4
m = 4
p = 1.0
## Set up world environment
environment = Environment(n, m, p)
## Main loop
MAX_ACTIONS = max_steps # prevent from running forever
num_actions = 0
num_clean_cells = [0] * max_steps
running = True
while (running and num_actions < MAX_ACTIONS):
# print current world
print "Action " + str(num_actions)
environment.printCurrentWorld()
# set up percept
percept = environment.getPercept()
# agent performs a step
action = agent.takeStep(percept)
# update environment and counters
running = environment.updateWorld(action)
# print num actions & num clean cells
num_clean_cells[num_actions] = environment.getNumCleanCells()
num_actions += 1
print str(num_actions) + ", " + str(num_clean_cells)
return num_clean_cells
print "******************************%d***************************************" % i
## Set up world environment
environment = Environment(n, m, p)
## Main loop
MAX_ACTIONS = 8000 # prevent from running forever
num_actions = 0
num_clean_cells = []
running = True
while (running and num_actions < MAX_ACTIONS):
# print current world
#print "Action " + str(num_actions)
#environment.printCurrentWorld()
# set up percept
percept = environment.getPercept()
# agent performs a step
action = agent.takeStep(percept)
print "---Action %d has been taken---" % action
# update environment and counters
running = environment.updateWorld(action)
num_actions += 1
# print num actions & num clean cells
num_clean_cells.append(environment.getNumCleanCells())
print "* " + str(num_actions) + ", " + str(num_clean_cells[num_actions-1])
# for randomized agent experiments
if num_clean_cells[num_actions-1] >= int(n*m*0.90):