def __init__(self,
graph_file,
agent_file,
cutoff_depth,
ping_pong,
mode='adversarial'):
self.ping_pong = ping_pong
self.graph_file = graph_file
self.time = 0 # track time of the world
self.evacuated = 0 # total number of people evacuated
self.agents_history = [] # search paths of smart agents
self.cutoff_depth = int(cutoff_depth)
self.world = World(graph_file=graph_file, k=self.prompt_k())
self.deadline = self.world.get_deadline()
self.agents = self.get_agents_data(agent_file=agent_file,
world=self.world)
self.init_state = self.create_init_states(self.world, self.agents)
self.mode = mode
if not ping_pong:
self.game_tree = GameTree(self.init_state,
self.world,
self.agents,
mode=mode,
cutoff_depth=self.cutoff_depth)
super(HurricaneGameSimulator, self).__init__(state=self.world,
agents=self.agents)
def __init__(self, graph_file, agent_file, f):
self.graph_file = graph_file
self.time = 0 # track time of the world
self.evacuated = 0 # total number of people evacuated
self.f_constant = f
self.agents_history = [] # search paths of smart agents
world = World(graph_file=graph_file, k=self.prompt_k())
self.deadline = world.get_deadline()
agents = self.get_agents_data(agent_file=agent_file, world=world)
super(HurricaneEvacuationSimulator, self).__init__(state=world,
agents=agents)
self.vandal_records = {} # pairs of <edge>:<time-of-blocking>
def __init__(self, graph_file, start_vertex):
self.graph_file = graph_file
self.world = World(graph_file=graph_file)
self.deadline = self.world.get_deadline()
self.shelter_tag = self.world.get_shelter_tag()
# create agent
self.start_vertex = start_vertex
self.time = 0 # track time of the world
self.evacuated = 0 # total number of people evacuated
self.belief_space = self.init_belief_space()
self.val_iterator = ValueIteration(self.belief_space, self.world)
self.utilities = self.val_iterator.value_iteration()
print(self.utilities.values())
from env import World
from model2 import Model
################################################################################################
parser = argparse.ArgumentParser()
parser.add_argument('--load', type=str, default=False,help='model to load')
parser.add_argument('--out',type=str, default='DQN.pth',help='output file')
parser.add_argument('--test', action='store_const',const=True,default=False,help='testing flag')
opt = parser.parse_args()
################################################################################################
################################################################################################
################################################################################################
################################################################################################
################################################################################################
from logger import Logger
env = World()
agent = Model(opt.load,mode='DDQN')
##########################################################################
#TRAIN THE VISOR
def train(n_episodes=50000, max_t=10, print_every=1, save_every=20):
logger = Logger('./logs')
scores_deque = deque(maxlen=200)
solved_deque = deque(maxlen=200)
scores= []
best = 0
for i_episode in count():
state = env.reset2_4(manual_pose=(i_episode % 200) + 1)
score = 0
class HurricaneGameSimulator(Simulator):
def __init__(self,
graph_file,
agent_file,
cutoff_depth,
ping_pong,
mode='adversarial'):
self.ping_pong = ping_pong
self.graph_file = graph_file
self.time = 0 # track time of the world
self.evacuated = 0 # total number of people evacuated
self.agents_history = [] # search paths of smart agents
self.cutoff_depth = int(cutoff_depth)
self.world = World(graph_file=graph_file, k=self.prompt_k())
self.deadline = self.world.get_deadline()
self.agents = self.get_agents_data(agent_file=agent_file,
world=self.world)
self.init_state = self.create_init_states(self.world, self.agents)
self.mode = mode
if not ping_pong:
self.game_tree = GameTree(self.init_state,
self.world,
self.agents,
mode=mode,
cutoff_depth=self.cutoff_depth)
super(HurricaneGameSimulator, self).__init__(state=self.world,
agents=self.agents)
# return num of actions for each agent
def get_all_actions(self):
agent_actions = {}
for agent in self.agents:
agent_actions[agent.name] = len(agent.get_actions())
return agent_actions
# return number of all people evacuated for ALL agents
def get_total_evacuated(self):
acc = 0
for agent in self.agents:
acc += agent.get_evacuated()
return acc
# move agent to the destination
def move_agent_to(self, agent, dest, edge):
agent.vertex = dest # move the agent
moving_time = self.calculate_price(agent=agent, edge=edge)
self.time += moving_time # add total time of simulator
# if deadline has passed, return
if self.time > self.deadline:
return False
if agent.observation.is_house(agent.vertex):
agent.pick_up()
elif agent.get_people_in_car() > 0: # if in a Shelter vertex
agent.drop_off()
return True
# time it takes to traverse on 'edge'
def calculate_price(self, agent, edge):
w = edge.weight
k = self.state.get_slow_down()
p = agent.get_people_in_car()
return w * (1 + k * p)
# Do a 1step for a Human & Greedy Agent
def do_agent(self, agent):
next_move = agent.do() # do action for Human Agent
agent.add_action(next_move)
if next_move == 'NOP':
self.time += 1
else: # Traverse
if next_move[0].upper() != 'T':
raise Exception('Unknown action')
dest = int(next_move[1:]) # number of the destination vertex
edge_to_traverse = self.state.get_edge(agent.vertex, dest)
return self.move_agent_to(agent=agent,
edge=edge_to_traverse,
dest=dest)
# input in the format of : H1 G3; <Type|Vertex>
def get_agents_data(self, world, agent_file=None):
num_human = 0
num_gamers = 0
agents = []
if agent_file is not None:
with open(agent_file) as agents_file:
for line in agents_file.readlines():
for agent_symbol in line.split():
vertex_number = int(agent_symbol[1:])
choice = 'MAX' if len(agents) == 0 else 'MIN'
if agent_symbol.upper().startswith('H'):
name = 'Human-{}'.format(str(num_human))
agent = Human(world=world,
name=name,
init_vertex=vertex_number,
choice=choice)
agents.append(agent)
num_human += 1
elif agent_symbol.upper().startswith('G'):
choice = 'MAX' if len(agents) == 0 else 'MIN'
name = 'Gamer-{}'.format(str(num_gamers))
agent = GameTreeAgent(world=world,
name=name,
init_vertex=vertex_number,
choice=choice)
agents.append(agent)
num_gamers += 1
return agents
# prompt the user for the K - slow down constant
def prompt_k(self):
k = float(input('Enter the slow-down constant: '))
# 0 < K < 1
if 0 < k <= 1:
return k
raise Exception('K must be in range (0,1)')
# create a path of states from the final node. the path is the agent's actions.
def get_state_path(self, final_node):
path = [final_node]
if final_node == 'FAILURE':
return ['FAILURE']
runner_node = final_node.parent
while runner_node is not None:
path.insert(0, runner_node)
runner_node = runner_node.parent
return path
# get the number of people saved by the Agent
def get_score_from_path(self, state_path):
score = 0
for i in range(len(state_path))[1:]:
in_car = state_path[i].get_people_in_car()
# if 0 people in car, it means last state was a drop-off
if in_car is 0:
score += state_path[i - 1].get_people_in_car()
return score
def print_run(self):
if len(self.agents_history) is 0:
print('Nothing to print!')
return
for agent, state_path in self.agents_history:
actions = [node.action for node in state_path]
score = self.get_score_from_path(state_path)
expands = self.agents[-1].expands
p = self.f_constant * score + expands
print('**********\nShowing steps of {}.\nscore:{}\nExpands:{}'.
format(agent, score, expands))
print('Performance: {} = {} * {} + {}'.format(
p, self.f_constant, score, expands))
print('Final State: {}\n\n'.format(state_path[len(state_path) -
1].state))
print('Action Trace:\n {}\n'.format(actions))
# create a state for 2 agent problem
def create_init_states(self, world, agents):
state = dict()
for agent in agents:
people = world.get_vertex_for_tag(
agent.vertex).people if world.is_house(agent.vertex) else 0
state[agent.name] = {
'position': agent.vertex,
'people_in_car': people,
'people_saved': 0
}
state['time'] = 0
return state
# run each agent in turn. in case of human agent, CHANGE the parent according to the human's choice.
def run(self):
print('initial state : {}'.format(self.game_tree.root.get_state()))
node = self.game_tree.root
i = 0 # first agent to "run"
while node.type is not 'CUTOFF' and node.type is not 'TERMINAL':
agent = self.agents[i]
action = agent.get_move(node)
# update to next node
for child in node.children:
if child.action == action:
child.parent = node
node = child
state_path = self.get_state_path(node)
print('path here : {}'.format([n.action for n in state_path]))
print(
'------\nagent:{} action {}\ntime: {}\nminimax value: {}\nstate: {}\n------\n'
.format(agent.name, action, node.get_time(),
node.get_minimax_value(), node.get_state()))
# next agent
i = (i + 1) % len(self.agents)
def run_ping_pong(self):
turn = 0
actions = []
visited = []
state = self.create_init_states(self.world, self.agents)
visited.append(
state[self.agents[0].name]['position']) # append initial positions
visited.append(
state[self.agents[1].name]['position']) # append initial positions
while True:
current_agent = self.agents[turn]
if isinstance(current_agent, Human):
result_node = current_agent.get_move(state=state,
visited=visited,
world=self.world)
else:
result_node = current_agent.get_move_new_tree(
state=state,
visited=visited,
world=self.world,
cutoff_depth=self.cutoff_depth,
mode=self.mode)
actions.append(result_node.action)
visited.append(result_node.get_position(current_agent.name))
visited.append(result_node.get_position(current_agent.name))
print('path here : {}'.format(actions))
print(
'------\nagent:{} action {}\ntime: {}\nminimax value: {}\nstate: {}\n------\n'
.format(self.agents[turn].choice, result_node.action,
result_node.get_time(),
result_node.get_minimax_value(),
result_node.get_state()))
if result_node.type == 'CUTOFF' or result_node.type == 'TERMINAL':
print("final state: {}".format(result_node.get_state()))
break
turn = (turn + 1) % len(self.agents) # next agent's turn
state = result_node.get_state()
result_node = None
class HurricaneEvacuationSimulator(object):
def __init__(self, graph_file, start_vertex):
self.graph_file = graph_file
self.world = World(graph_file=graph_file)
self.deadline = self.world.get_deadline()
self.shelter_tag = self.world.get_shelter_tag()
# create agent
self.start_vertex = start_vertex
self.time = 0 # track time of the world
self.evacuated = 0 # total number of people evacuated
self.belief_space = self.init_belief_space()
self.val_iterator = ValueIteration(self.belief_space, self.world)
self.utilities = self.val_iterator.value_iteration()
print(self.utilities.values())
# initialize the belief space for the graph
def init_belief_space(self):
bs = BeliefSpace(self.world, init_vertex=int(args.start_vertex))
bs.create_all_belief_states(self.start_vertex)
return bs
# generate all possible blockage combinations
def all_blockage_instances(self):
# edge that can be blocked
maybe_blocked = map(
lambda e: e.edge_num,
filter(lambda e: e.prob_blockage > 0,
self.world.get_edges(one_way=True)))
blockages = set(product({True, False}, repeat=len(maybe_blocked)))
return [dict(zip(maybe_blocked, blockage)) for blockage in blockages]
def random_blockage(self):
# blockable edges
blockables = map(
lambda e: e.edge_num,
filter(lambda e: e.prob_blockage > 0,
self.world.get_edges(one_way=True)))
# NONE at first
blockage_dict = {key: None for key in blockables}
for e in blockage_dict:
prob = self.world.get_edge_for_num(e).prob_blockage
blockage_dict[e] = self.true_in_prob(prob)
return blockage_dict
# return 'True' in probability of 'prob'
def true_in_prob(self, prob):
rand = random.random()
return True if rand <= prob else False
def run_an_agent(self, times=10000):
util_acc = 0.0
init_s = None
for i in range(times):
blockage_instance = self.random_blockage()
init_states = self.belief_space.init_states
# remove from init state/s
init_state = filter(
lambda d: self.consistent_state(d, blockage_instance),
init_states)[0]
init_s = init_state
agent = PlanningAgent(world=self.world, belief_space=self.belief_space, utilities=self.utilities, \
init_state=init_state, init_vertex=self.start_vertex, blockage=blockage_instance)
next_state = agent.state
while not self.belief_space.goal_state(next_state) and not (len(
next_state.successors) == 0):
next_state = agent.do()
util_acc += self.utilities[
next_state] #self.belief_space.states.index(next_state)]
print('i: {}\nacc: {}'.format(i, util_acc))
#print('accumulated: {}'.format(util_acc))
print('average: {}'.format(util_acc / times))
print('init value: {}'.format(
self.utilities[self.belief_space.states[0]]))
def consistent_state(self, belief_state, blockage_instance):
state_blocked = belief_state.blocked_edges
for edge_num in state_blocked:
if blockage_instance[edge_num] != state_blocked[edge_num]:
return False
return True
def __init__(self, graph_file):
self.graph_file = graph_file
self.world = World(graph_file=graph_file)
self.deadline = self.world.get_deadline()
self.bayes_network = BayesNetwork(world=self.world)
self.reports = {}
class Main(object):
def __init__(self, graph_file):
self.graph_file = graph_file
self.world = World(graph_file=graph_file)
self.deadline = self.world.get_deadline()
self.bayes_network = BayesNetwork(world=self.world)
self.reports = {}
def clear_screen(self, stupid=False):
if stupid:
print('\n') * 100
else:
os.system('cls' if os.name == 'nt' else 'clear')
def get_numbers(self, prompt, smallest, biggest):
while True:
choice = raw_input(prompt).split()
if 'exit' in choice or 'quit' in choice or 'q' in choice:
exit()
elif not any(
int(x) < smallest or int(x) > biggest
for x in choice) and not len(choice) == 0:
# self.clear_screen(stupid=True)
return choice
else:
# self.clear_screen(stupid=True)
print('illegal input.')
return False
# get query evidence from user
def prompt_query_evidence(self):
all_reports = {}
num_edges = len(self.world.get_edges(one_way=True))
num_vertices = len(self.world.get_vertices())
report_prompt = 'What would you like to report? \n 1. Flood\n 2. Blockage\n 3. Evacuees\n-------\n ' \
'4. No Flood\n 5. No Blockage\n 6. No Evacuees\n-------\n 7. Non-Blocked Path\n 8. Print Reasoning\n 9. Bonus\n 10. Reset\n choice: '
short_report_prompt = '\nAnother report?'
blockage_prompt = 'report Blocking at edges : range-({},{}) '.format(
1, num_edges)
flooding_prompt = 'report Flooding at vertices range-({},{}) : '.format(
1, num_vertices)
evacuees_prompt = 'report Evacuees at vertices range-({},{}): '.format(
1, num_vertices)
non_blockage_prompt = 'report NON Blocking at edges : range-({},{}) '.format(
1, num_edges)
non_flooding_prompt = 'report NON Flooding at vertices range-({},{}) : '.format(
1, num_vertices)
non_evacuees_prompt = 'report NON Evacuees at vertices range-({},{}): '.format(
1, num_vertices)
iteration = 0
while True:
iteration += 1
print(
'\n----------------\nReported so far : \n{}\n----------------'
.format(all_reports))
if iteration is 1:
report_choice = int(
self.get_numbers(report_prompt, smallest=1, biggest=10)[0])
else:
report_choice = int(
self.get_numbers(short_report_prompt,
smallest=1,
biggest=10)[0])
if report_choice == 1:
floodings = set(
self.get_numbers(flooding_prompt,
smallest=1,
biggest=num_vertices))
floodings = set(['flooding ' + str(num) for num in floodings])
for report in floodings:
all_reports[report] = True
elif report_choice == 2:
blockages = set(
self.get_numbers(blockage_prompt,
smallest=1,
biggest=num_edges))
blockages = set(['blockage ' + str(num) for num in blockages])
for report in blockages:
all_reports[report] = True
elif report_choice == 3:
evacuees = set(
self.get_numbers(evacuees_prompt,
smallest=1,
biggest=num_vertices))
evacuees = set(['evacuees ' + str(num) for num in evacuees])
for report in evacuees:
all_reports[report] = True
elif report_choice == 4:
floodings = set(
self.get_numbers(non_flooding_prompt,
smallest=1,
biggest=num_vertices))
floodings = set(['flooding ' + str(num) for num in floodings])
for report in floodings:
all_reports[report] = False
elif report_choice == 5:
blockages = set(
self.get_numbers(non_blockage_prompt,
smallest=1,
biggest=num_edges))
blockages = set(['blockage ' + str(num) for num in blockages])
for report in blockages:
all_reports[report] = False
elif report_choice == 6:
evacuees = set(
self.get_numbers(non_evacuees_prompt,
smallest=1,
biggest=num_vertices))
evacuees = set(['evacuees ' + str(num) for num in evacuees])
for report in evacuees:
all_reports[report] = False
elif report_choice == 7:
print('Overall Reported: {}'.format(all_reports))
prompt = 'Enter a set of Edges as a path. range-({},{}) '.format(
1, num_edges)
path = set(
int(n) for n in self.get_numbers(
prompt, smallest=1, biggest=num_edges))
if len(path) > 1:
self.reports = all_reports
p = self.get_probability_path_free(path)
non_blocked = ', '.join(
['not blockage {}'.format(str(e)) for e in path])
given = self.evidence_as_string(all_reports)
s = 'P({of} | {given} ) = {p}'.format(of=non_blocked,
given=given,
p=p)
print(s)
else:
print('A single edge can computed normally')
elif report_choice == 8:
print('Overall Reported: {}'.format(all_reports))
self.reports = all_reports
self.perform_reasoning()
elif report_choice == 9:
self.reports = all_reports
print('Overall Reported: {}'.format(all_reports))
prompt = 'Enter a source Vertex and a Destination Vertex. range-({},{}) '.format(
1, num_vertices)
user_input = [
int(n) for n in self.get_numbers(
prompt, smallest=1, biggest=num_vertices)
]
if len(user_input) is not 2:
print('usage : <source> <destination>')
else:
self.reports = all_reports
self.do_bonus(source=user_input[0],
destination=user_input[1])
elif report_choice == 10:
all_reports = dict()
# print the network
def print_network(self):
self.bayes_network.print_network()
def perform_reasoning(self):
self.query_type('evacuees')
self.query_type('flooding')
self.query_type('blockage')
def query_type(self, node_type, for_print=True):
nodes = self.bayes_network.get_nodes_of_type(node_type)
vals = []
for node in nodes:
# self.enumerate_prob(node)
if node.node_type != 'blockage':
vals.append((node.get_vertex().tag, self.enumerate_prob(node)))
else:
vals.append(
(node.get_edge().edge_num, self.enumerate_prob(node)))
return vals
def do_bonus(self, source, destination):
paths = self.world.all_paths(source=source, destination=destination)
probabilities = [self.get_probability_path_free(p) for p in paths]
print(
'Printing the Probability of free from blockages - path from {} to {} :'
.format(source, destination))
min_path = ([], 0.0)
for (path, prob) in zip(paths, probabilities):
if prob >= min_path[1]:
min_path = (path, prob)
print('Path: {} , Probability(free) = {}'.format(path, prob))
print('\n===========================\n')
if min_path[1] == 0.0:
print('all paths from {} to {} are blocked with probability 1'.
format(source, destination))
else:
print('Best path is : {} with probability {}'.format(
min_path[0], min_path[1]))
# and print
def enumerate_prob(self, node):
enumerator = Enumerator(query_var=node,
evidence=self.reports,
network=self.bayes_network)
p = enumerator.pretty_string(query_value=True)
p_val = enumerator.enumeration_ask()
s = p + str(p_val[0])
print(s)
# print("\n")
return p_val[0]
def get_probability_path_free(self, path):
reported_evidence = self.reports.copy()
query_vars = filter(lambda n: n.get_edge().edge_num in path,
self.bayes_network.get_nodes_of_type('blockage'))
multi_query = MultiQuery(query_vars=query_vars,
evidence=reported_evidence,
network=self.bayes_network)
# vars_true is False - we want blockages to be false.
p = multi_query.query_to_value(vars_true=False)
return p
def evidence_as_string(self, evidence):
s = ''
for e in evidence.keys():
if s != '':
s += ','
if evidence[e]:
s += e
else:
s += 'not ' + e
return s
class HurricaneEvacuationSimulator(Simulator):
def __init__(self, graph_file, agent_file, f):
self.graph_file = graph_file
self.time = 0 # track time of the world
self.evacuated = 0 # total number of people evacuated
self.f_constant = f
self.agents_history = [] # search paths of smart agents
world = World(graph_file=graph_file, k=self.prompt_k())
self.deadline = world.get_deadline()
agents = self.get_agents_data(agent_file=agent_file, world=world)
super(HurricaneEvacuationSimulator, self).__init__(state=world,
agents=agents)
self.vandal_records = {} # pairs of <edge>:<time-of-blocking>
# return num of actions for each agent
def get_all_actions(self):
agent_actions = {}
for agent in self.agents:
agent_actions[agent.name] = len(agent.get_actions())
return agent_actions
# return number of all people evacuated for ALL agents
def get_total_evacuated(self):
acc = 0
for agent in self.agents:
acc += agent.get_evacuated()
return acc
# move agent to the destination
def move_agent_to(self, agent, dest, edge):
agent.vertex = dest # move the agent
moving_time = self.calculate_price(agent=agent, edge=edge)
self.time += moving_time # add total time of simulator
# if deadline has passed, return
if self.time > self.deadline:
return False
if agent.observation.is_house(
agent.vertex) and not isinstance(agent, Vandal):
agent.pick_up()
elif agent.get_people_in_car() > 0: # if in a Shelter vertex
agent.drop_off()
return True
# time it takes to traverse on 'edge'
def calculate_price(self, agent, edge):
w = edge.weight
k = self.state.get_slow_down()
p = agent.get_people_in_car()
return w * (1 + k * p)
# Do a 1step for a Human & Greedy Agent
def do_agent(self, agent):
next_move = agent.do() # do action for Human Agent
agent.add_action(next_move)
if next_move == 'NOP':
self.time += 1
else: # Traverse
if next_move[0].upper() != 'T':
raise Exception('Unknown action')
dest = int(next_move[1:]) # number of the destination vertex
edge_to_traverse = self.state.get_edge(agent.vertex, dest)
return self.move_agent_to(agent=agent,
edge=edge_to_traverse,
dest=dest)
# Do a step for a Vandal Agent
def do_vandal(self, agent):
next_move = agent.do() # do action for Vandal Agent
agent.add_action(next_move)
if next_move == 'NOP':
self.time += 1
elif str(next_move).startswith('BLOCK'):
v1 = int(next_move.split()[1])
v2 = int(next_move.split()[2])
to_block = self.state.get_edge(v1, v2)
to_block.blocked = True
self.time += 1
self.record_block(v1, v2)
else: # Traverse
if next_move[0].upper() != 'T':
raise Exception('Unknown action')
dest = int(next_move[1:]) # number of the destination vertex
edge_to_traverse = self.state.get_edge(agent.vertex, dest)
return self.move_agent_to(agent=agent,
edge=edge_to_traverse,
dest=dest)
# Do a step for a Vandal Agent
def simulate_vandal(self, agent):
while self.time <= self.deadline:
self.do_vandal(agent=agent)
# re-create the world
self.state = World(graph_file=self.graph_file,
k=self.state.get_slow_down())
# input in the format of : H1 V3 G10 H2 ; <Type|Vertex>
def get_agents_data(self, world, agent_file=None):
num_human = 0
num_greedy = 0
num_vandal = 0
agents = []
if agent_file is not None:
with open(agent_file) as agents_file:
for line in agents_file.readlines():
for agent_symbol in line.split():
vertex_number = int(agent_symbol[1:])
if agent_symbol.upper().startswith('H'):
agent = Human(world=world,
name='Human-{}'.format(
str(num_human)),
init_vertex=vertex_number)
num_human += 1
elif agent_symbol.upper().startswith('G'):
agent = Greedy(world=world,
name='Greedy-{}'.format(
str(num_greedy)),
init_vertex=vertex_number)
num_greedy += 1
else: # agent_symbol.upper().startswith('V')
agent = Vandal(world=world,
name='Vandal-{}'.format(
str(num_vandal)),
init_vertex=vertex_number)
num_vandal += 1
agents.append(agent)
return agents
# prompt the user for the K - slow down constant
def prompt_k(self):
k = 1 #float(input('Enter the slow-down constant: '))
# 0 < K < 1
if 0 < k <= 1:
return k
raise Exception('K must be in range (0,1)')
def run_task1(self):
print('DEADLINE IS {}'.format(self.deadline))
# First round of pick-ups
for agent in self.agents:
if isinstance(agent, Human) or isinstance(agent, Greedy):
agent.pick_up()
while self.time < self.deadline:
for agent in self.agents:
if isinstance(agent, Human) or isinstance(agent, Greedy):
if isinstance(agent, Human):
agent.print_agent_status()
if self.do_agent(agent=agent) is False:
continue
if isinstance(agent, Vandal):
if self.do_vandal(agent=agent) is False:
break
if self.time >= self.deadline:
break
print('Time : {}\n---------'.format(self.time))
agent.print_agent_status()
# self.state.print_graph()
print('----step done, time {}----\n\n'.format(self.time))
def run_task2(self, expand_limit, agent="greedy"):
agent_type = agent
print(agent_type)
if agent_type.lower() == "greedy":
smart_agent = SmartGreedy(world=self.state,
name='SmartGreedy',
init_vertex=1)
elif agent_type.lower() == "a*":
smart_agent = SmartAStar(world=self.state,
name='SmartAStar',
init_vertex=1)
else: #if agent.upper() is "RTA":
smart_agent = SmartRTA(world=self.state,
name='RTA',
init_vertex=1,
expand_limit=expand_limit)
self.agents.append(smart_agent)
final_node = smart_agent.do()
self.agents_history.append(
(agent_type, self.get_state_path(final_node)))
self.print_run()
def run_bonus(self, expand_limit, agent="greedy", vandal_init_vertex=1):
vandal = Vandal(world=self.state,
init_vertex=vandal_init_vertex,
name='Vandal_Agents')
self.simulate_vandal(vandal) # run the vandal
print(
'------------\nThe Vandal records are: {}\n------------\n'.format(
self.vandal_records))
agent_type = agent
print(agent_type)
if agent_type.lower() == "greedy":
smart_agent = SmartGreedy(world=self.state,
name='SmartGreedy',
init_vertex=1,
bonus_vandal_records=self.vandal_records)
elif agent_type.lower() == "a*":
smart_agent = SmartAStar(world=self.state,
name='SmartAStar',
init_vertex=1,
bonus_vandal_records=self.vandal_records)
else: #if agent.upper() is "RTA":
smart_agent = SmartRTA(world=self.state,
name='RTA',
init_vertex=1,
expand_limit=expand_limit,
bonus_vandal_records=self.vandal_records)
self.agents.append(smart_agent)
final_node = smart_agent.do()
self.agents_history.append(
(agent_type, self.get_state_path(final_node)))
self.print_run()
# vandal = Vandal(world=self.state, init_vertex=vandal_init_vertex, name='Vandal_Agents')
#
# agent_type = agent
# print(agent_type)
# if agent_type.lower() == "greedy":
# smart_agent = SmartGreedy(world=self.state, name='SmartGreedy', init_vertex=1)
# elif agent_type.lower() == "a*":
# smart_agent = SmartAStar(world=self.state, name='SmartAStar', init_vertex=1)
# else: #if agent.upper() is "RTA":
# smart_agent = SmartRTA(world=self.state, name='RTA', init_vertex=1, expand_limit=expand_limit)
#
# self.agents.append(smart_agent)
# final_node = smart_agent.do()
# nodes = smart_agent.search_tree.get_visited_vertices(final_node)
# smart_node = nodes[-1]
#
# while smart_node.get_time() <= self.deadline:
# # "advance" the smart agent one step
# smart_node = smart_agent.search_tree.get_next_node_in_path(smart_node, final_node)
# state = smart_node.get_state()
# # advance time as the smart agent's step
# self.time = smart_node.get_time()
# # run one step of the vandal
# self.do_vandal(vandal)
# # state[]
# create a path of states from the final node. the path is the agent's actions.
def get_state_path(self, final_node):
path = [final_node]
if final_node == 'FAILURE':
return ['FAILURE']
runner_node = final_node.parent
while runner_node is not None:
path.insert(0, runner_node)
runner_node = runner_node.parent
return path
# get the number of people saved by the Agent
def get_score_from_path(self, state_path):
score = 0
for i in range(len(state_path))[1:]:
in_car = state_path[i].get_people_in_car()
# if 0 people in car, it means last state was a drop-off
if in_car is 0:
score += state_path[i - 1].get_people_in_car()
return score
# def get_rescue_list_from_path(self, state_path):
# rescue_list = []
# for i in range(len(state_path)):
# rescue_list.append(' ')
# in_car = state_path[i].get_people_in_car()
# if in_car > state_path[i - 1].get_people_in_car():
# rescue_list[i] = 'picked up : {}'.format(in_car)
# elif in_car < state_path[i - 1].get_people_in_car():
# rescue_list[i] = 'dropped off : {}'.format(state_path[i - 1].get_people_in_car())
# return rescue_list
def print_run(self):
if len(self.agents_history) is 0:
print('Nothing to print!')
return
for agent, state_path in self.agents_history:
actions = [node.action for node in state_path]
score = self.get_score_from_path(state_path)
expands = self.agents[-1].expands
p = self.f_constant * score + expands
print('**********\nShowing steps of {}.\nscore:{}\nExpands:{}'.
format(agent, score, expands))
print('Performance: {} = {} * {} + {}'.format(
p, self.f_constant, score, expands))
print('Final State: {}\n\n'.format(state_path[len(state_path) -
1].state))
print('Action Trace:\n {}\n'.format(actions))
def record_block(self, v1, v2):
edge1 = '{},{}'.format(str(v1), str(v2))
edge2 = '{},{}'.format(str(v2), str(v1))
self.vandal_records[edge1] = self.time
self.vandal_records[edge2] = self.time
def simulate_vandal(self, agent):
while self.time <= self.deadline:
self.do_vandal(agent=agent)
# re-create the world
self.state = World(graph_file=self.graph_file,
k=self.state.get_slow_down())
