def construct_training_env():
config = {
'observation_type':
'tensor',
'agent_speed_range': [-3, -1],
'finish_position':
Point(0, 0),
'random_seed':
15,
'stochasticity':
1.,
'lanes': [
LaneSpec(cars=7, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -1]),
LaneSpec(cars=6, speed_range=[-1, -1]),
LaneSpec(cars=6, speed_range=[-3, -1]),
LaneSpec(cars=7, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -1]),
LaneSpec(cars=6, speed_range=[-3, -2]),
LaneSpec(cars=7, speed_range=[-1, -1]),
LaneSpec(cars=6, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -2])
],
'width':
50,
'tensor_state':
True,
'flicker_rate':
0.,
'mask':
None
}
return gym.make('GridDriving-v0', **config)
def get_env():
'''
Get the sample test cases for training and testing.
'''
# config = { 'observation_type': 'tensor', 'agent_speed_range': [-2, -1], 'stochasticity': 0.0, 'width': 10,
# 'lanes': [
# LaneSpec(cars=3, speed_range=[-2, -1]),
# LaneSpec(cars=4, speed_range=[-2, -1]),
# LaneSpec(cars=2, speed_range=[-1, -1]),
# LaneSpec(cars=2, speed_range=[-3, -1])
# ] }
#
config = {'observation_type': 'tensor', 'agent_speed_range': [-3, -1], 'width': 50,
'lanes': [LaneSpec(cars=7, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -1]),
LaneSpec(cars=6, speed_range=[-1, -1]),
LaneSpec(cars=6, speed_range=[-3, -1]),
LaneSpec(cars=7, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -1]),
LaneSpec(cars=6, speed_range=[-3, -2]),
LaneSpec(cars=7, speed_range=[-1, -1]),
LaneSpec(cars=6, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -2])]
}
return gym.make('GridDriving-v0', **config)
def construct_train_task2_env():
random_car = numpy.random.randint(5, 10, 10)
speed_range = [[-3, -3], [-3, -2], [-3, -1], [-2, -2], [-2, -1], [-1, -1]]
random_speed_range = random.sample(speed_range, 10)
config = {
'observation_type':
'tensor',
'agent_speed_range': [-3, -1],
'width':
50,
'lanes': [
LaneSpec(cars=random_car[0], speed_range=random_speed_range[0]),
LaneSpec(cars=random_car[1], speed_range=random_speed_range[1]),
LaneSpec(cars=random_car[2], speed_range=random_speed_range[2]),
LaneSpec(cars=random_car[3], speed_range=random_speed_range[3]),
LaneSpec(cars=random_car[4], speed_range=random_speed_range[4]),
LaneSpec(cars=random_car[5], speed_range=random_speed_range[5]),
LaneSpec(cars=random_car[6], speed_range=random_speed_range[6]),
LaneSpec(cars=random_car[7], speed_range=random_speed_range[7]),
LaneSpec(cars=random_car[8], speed_range=random_speed_range[8]),
LaneSpec(cars=random_car[9], speed_range=random_speed_range[9])
]
}
return gym.make('GridDriving-v0', **config)
def construct_task_env():
config = {
'observation_type':
'tensor',
'agent_speed_range': [-3, -1],
'width':
50,
'lanes': [
LaneSpec(cars=7, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -1]),
LaneSpec(cars=6, speed_range=[-1, -1]),
LaneSpec(cars=6, speed_range=[-3, -1]),
LaneSpec(cars=7, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -1]),
LaneSpec(cars=6, speed_range=[-3, -2]),
LaneSpec(cars=7, speed_range=[-1, -1]),
LaneSpec(cars=6, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -2])
]
}
return gym.make('GridDriving-v0', **config)
# Easier env
# def construct_task_env():
# config = {'observation_type': 'tensor', 'agent_speed_range': [-3, -1], 'stochasticity': 1.0, 'width': 50,
# 'lanes': [LaneSpec(cars=3, speed_range=[-2, -1]),
# LaneSpec(cars=4, speed_range=[-2, -1]),
# LaneSpec(cars=3, speed_range=[-1, -1]),
# LaneSpec(cars=4, speed_range=[-3, -1]),
# LaneSpec(cars=4, speed_range=[-2, -1]),
# LaneSpec(cars=3, speed_range=[-2, -1]),
# LaneSpec(cars=2, speed_range=[-3, -2]),
# LaneSpec(cars=3, speed_range=[-1, -1]),
# LaneSpec(cars=2, speed_range=[-2, -1]),
# LaneSpec(cars=3, speed_range=[-2, -2])]
# }
# return gym.make('GridDriving-v0', **config)
# def construct_task_env():
# config = { 'observation_type': 'tensor', 'agent_speed_range': [-3, -1], 'stochasticity': 1.0, 'width': 20,
# 'lanes': [
# LaneSpec(cars=2, speed_range=[-2, -1]),
# LaneSpec(cars=1, speed_range=[-2, -1]),
# LaneSpec(cars=2, speed_range=[-1, -1]),
# LaneSpec(cars=1, speed_range=[-3, -1]),
# LaneSpec(cars=1, speed_range=[-3, -1]),
# LaneSpec(cars=2, speed_range=[-2, -1]),
# LaneSpec(cars=1, speed_range=[-2, -1]),
# LaneSpec(cars=1, speed_range=[-1, -1]),
# LaneSpec(cars=2, speed_range=[-3, -1]),
# LaneSpec(cars=1, speed_range=[-3, -1])
# ]}
# return gym.make('GridDriving-v0', **config)
def construct_task2_env():
config = {'observation_type': 'tensor', 'agent_speed_range': [-3, -1], 'width': 50,
'lanes': [LaneSpec(cars=7, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -1]),
LaneSpec(cars=6, speed_range=[-1, -1]),
LaneSpec(cars=6, speed_range=[-3, -1]),
LaneSpec(cars=7, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -1]),
LaneSpec(cars=6, speed_range=[-3, -2]),
LaneSpec(cars=7, speed_range=[-1, -1]),
LaneSpec(cars=6, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -2])]
}
return gym.make('GridDriving-v0', **config)
def construct_random_lane_env(): #Tensor version for DQN
config = {'observation_type': 'tensor', 'agent_speed_range': [-3, -1], 'width': 50,
'lanes': [LaneSpec(cars=7, speed_range=[-3, -1]),
LaneSpec(cars=8, speed_range=[-3, -1]),
LaneSpec(cars=6, speed_range=[-3, -1]),
LaneSpec(cars=6, speed_range=[-3, -1]),
LaneSpec(cars=7, speed_range=[-3, -1]),
LaneSpec(cars=8, speed_range=[-3, -1]),
LaneSpec(cars=6, speed_range=[-3, -1]),
LaneSpec(cars=7, speed_range=[-3, -1]),
LaneSpec(cars=6, speed_range=[-3, -1]),
LaneSpec(cars=8, speed_range=[-3, -1])],
'random_lane_speed': True
}
return gym.make('GridDriving-v0', **config)
def get_env():
'''
Get the sample test cases for training and testing.
'''
config = {
'agent_speed_range': [-3, -1],
'width':
50,
'lanes': [
LaneSpec(cars=7, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -1]),
LaneSpec(cars=6, speed_range=[-1, -1]),
LaneSpec(cars=6, speed_range=[-3, -1]),
LaneSpec(cars=7, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -1]),
LaneSpec(cars=6, speed_range=[-3, -2]),
LaneSpec(cars=7, speed_range=[-1, -1]),
LaneSpec(cars=6, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -2])
]
}
return gym.make('GridDriving-v0', **config)
def construct_random_lane_env():
config = {
"observation_type":
"tensor",
"agent_speed_range": [-3, -1],
"width":
50,
"lanes": [
LaneSpec(cars=7, speed_range=[-3, -1]),
LaneSpec(cars=8, speed_range=[-3, -1]),
LaneSpec(cars=6, speed_range=[-3, -1]),
LaneSpec(cars=6, speed_range=[-3, -1]),
LaneSpec(cars=7, speed_range=[-3, -1]),
LaneSpec(cars=8, speed_range=[-3, -1]),
LaneSpec(cars=6, speed_range=[-3, -1]),
LaneSpec(cars=7, speed_range=[-3, -1]),
LaneSpec(cars=6, speed_range=[-3, -1]),
LaneSpec(cars=8, speed_range=[-3, -1])
],
"random_lane_speed":
True
}
return gym.make("GridDriving-v0", **config)
def get_env(cars=7, tensor=False):
'''
Get the sample test cases for training and testing.
'''
# config = {'agent_speed_range': [-3, -1], 'width': 50,
# 'lanes': [LaneSpec(cars=7, speed_range=[-2, -1]),
# LaneSpec(cars=8, speed_range=[-2, -1]),
# LaneSpec(cars=6, speed_range=[-1, -1]),
# LaneSpec(cars=6, speed_range=[-3, -1]),
# LaneSpec(cars=7, speed_range=[-2, -1]),
# LaneSpec(cars=8, speed_range=[-2, -1]),
# LaneSpec(cars=6, speed_range=[-3, -2]),
# LaneSpec(cars=7, speed_range=[-1, -1]),
# LaneSpec(cars=6, speed_range=[-2, -1]),
# LaneSpec(cars=8, speed_range=[-2, -2])]
# }
config = {
'agent_speed_range': [-3, -1],
'width':
50,
'lanes': [
LaneSpec(cars=cars, speed_range=[-2, -1]),
LaneSpec(cars=cars, speed_range=[-2, -1]),
LaneSpec(cars=cars, speed_range=[-1, -1]),
LaneSpec(cars=cars, speed_range=[-3, -1]),
LaneSpec(cars=cars, speed_range=[-2, -1]),
LaneSpec(cars=cars, speed_range=[-2, -1]),
LaneSpec(cars=cars, speed_range=[-3, -2]),
LaneSpec(cars=cars, speed_range=[-1, -1]),
LaneSpec(cars=cars, speed_range=[-2, -1]),
LaneSpec(cars=cars, speed_range=[-2, -2])
]
}
if tensor:
config['observation_type'] = 'tensor'
return gym.make('GridDriving-v0', **config)
def construct_task1_env():
test_config = [{
'lanes': [LaneSpec(10, [-2, -2])] * 2 + [LaneSpec(10, [-3, -3])] * 2 +
[LaneSpec(8, [-4, -4])] * 2 + [LaneSpec(8, [-5, -5])] * 2 +
[LaneSpec(12, [-4, -4])] * 2 + [LaneSpec(12, [-3, -3])] * 2,
'width':
50,
'agent_speed_range': (-3, -1),
'random_seed':
11
}]
test_index = 0
case = test_config[test_index]
return gym.make('GridDriving-v0', **case)
def heuristic_reward():
# parse_sas_plan(pos_memo)
task2_env = construct_task2_env()
n_lanes, n_width, agent_speed_range = len(task2_env.lanes), task2_env.width, task2_env.agent_speed_range
pos_memo = [[0 if (x == 0 and y == 0) else None for y in range(n_lanes)] for x in range(n_width)]
lanes = [LaneSpec(0, [0, 0])] * n_lanes
for start_x in list(range(n_width))[::-1]:
for start_y in list(range(n_lanes))[::-1]:
if pos_memo[start_x][start_y] is None:
print("Start x: {} start y: {}".format(start_x, start_y))
env = gym.make('GridDriving-v0', lanes=lanes, width=n_width,
random_seed=42, agent_speed_range=(-3, -1), agent_pos_init=Point(x=start_x, y=start_y))
gen = initializeSystem(env)
generateDomainPDDLFile(gen)
generateProblemPDDLFile(gen)
runPDDLSolver(gen)
parse_sas_plan(pos_memo, start_x, start_y)
print("pos_memo:")
print(pos_memo)
pos_inf_reward, neg_inf_reward = 10, -10
for x in range(n_width):
for y in range(n_lanes):
if pos_memo[x][y] == 0:
pos_memo[x][y] = pos_inf_reward
elif pos_memo[x][y] == -1:
pos_memo[x][y] = neg_inf_reward
else:
pos_memo[x][y] = 1. / pos_memo[x][y]
print("Final reward matrix")
pos_memo = np.array(pos_memo)
print(pos_memo)
save_to_pickle(pos_memo, "reward_shaping.p")
SUBMISSION = False
import gym
import gym_grid_driving
from gym_grid_driving.envs.grid_driving import LaneSpec, Point
import os
import sys
test_config = [{
'lanes': [LaneSpec(2, [0, 0])] * 3,
'width': 5,
'seed': 13
}, {
'lanes': [LaneSpec(2, [0, 0])] * 3,
'width': 5,
'seed': 10
}, {
'lanes': [LaneSpec(3, [0, 0])] * 4,
'width': 10,
'seed': 25
}, {
'lanes': [LaneSpec(4, [0, 0])] * 4,
'width': 10,
'seed': 25
}, {
'lanes': [LaneSpec(8, [0, 0])] * 7,
'width': 20,
'seed': 25
}, {
'lanes': [LaneSpec(7, [0, 0])] * 10,
'width': 20,
'seed': 125
FAST_DOWNWARD_DIRECTORY_ABSOLUTE_PATH = "/fast_downward/"
else :
FAST_DOWNWARD_DIRECTORY_ABSOLUTE_PATH = ""
PDDL_FILE_ABSOLUTE_PATH = ""
##########################################################
### Sample test cases for Parking task.
# test_config = [{'lanes' : [LaneSpec(2, [0, 0])] *3,'width' :5, 'seed' : 13},
# {'lanes' : [LaneSpec(2, [0, 0])] *3,'width' :5, 'seed' : 10},
# {'lanes' : [LaneSpec(3, [0, 0])] *4,'width' :10, 'seed' : 25},
# {'lanes' : [LaneSpec(4, [0, 0])] *4,'width' :10, 'seed' : 25},
# {'lanes' : [LaneSpec(8, [0, 0])] *7,'width' :20, 'seed' : 25},
# {'lanes' : [LaneSpec(7, [0, 0])] *10,'width' :20, 'seed' : 125}]
### Sample test cases for Crossing Task
test_config = [{'lanes' : [LaneSpec(6, [-2, -2])] *2 + [LaneSpec(6, [-5, -5])] *2 +
[LaneSpec(5, [-4, -4])] *2 + [LaneSpec(5, [-2, -2])] *1, 'width' :30, 'seed' : 101}]
test_case_number = 0 # Change the index for a different test case
LANES = test_config[test_case_number]['lanes']
WIDTH = test_config[test_case_number]['width']
RANDOM_SEED = test_config[test_case_number]['seed']
class GeneratePDDL_Stationary :
'''
Class to generate the PDDL files given the environment description.
'''
def __init__ (self, env, num_lanes, width, file_name) :
self.state = env.reset()
self.num_lanes = num_lanes
Helper function to convert an env state to a state feature vector.
'''
cars = env.cars
done = env.done
state = []
for car in cars:
state += [car.position.x, car.position.y]
state.append(int(done == True))
return state
if not SUBMISSION:
### Sample test cases.
test_config = [{
'lanes': [LaneSpec(0, [-2, -1])] * 5,
'width': 9,
'gamma': 0.9,
'seed': 15,
'fin_pos': Point(0, 0),
'agent_pos': Point(8, 4),
'stochasticity': 1.
}, {
'lanes': [LaneSpec(1, [-2, -1])] * 2,
'width': 4,
'gamma': 0.9,
'seed': 15,
'fin_pos': Point(0, 1),
'agent_pos': Point(3, 1),
'stochasticity': 1.
}, {
import gym
import gym_grid_driving
from gym_grid_driving.envs.grid_driving import LaneSpec, Point
import os
################### DO NOT CHANGE THIS ###################
if not SUBMISSION:
FAST_DOWNWARD_DIRECTORY_ABSOLUTE_PATH = "/fast_downward/"
else:
FAST_DOWNWARD_DIRECTORY_ABSOLUTE_PATH = ""
PDDL_FILE_ABSOLUTE_PATH = ""
##########################################################
### Sample test cases for Parking task.
test_config = [{
'lanes': [LaneSpec(2, [0, 0])] * 3,
'width': 5,
'seed': 13
}, {
'lanes': [LaneSpec(2, [0, 0])] * 3,
'width': 5,
'seed': 10
}, {
'lanes': [LaneSpec(3, [0, 0])] * 4,
'width': 10,
'seed': 25
}, {
'lanes': [LaneSpec(4, [0, 0])] * 4,
'width': 10,
'seed': 25
}, {
else:
FAST_DOWNWARD_DIRECTORY_ABSOLUTE_PATH = ""
PDDL_FILE_ABSOLUTE_PATH = ""
##########################################################
### Sample test cases for Parking task.
# test_config = [{'lanes' : [LaneSpec(2, [0, 0])] *3,'width' :5, 'seed' : 13},
# {'lanes' : [LaneSpec(2, [0, 0])] *3,'width' :5, 'seed' : 10},
# {'lanes' : [LaneSpec(3, [0, 0])] *4,'width' :10, 'seed' : 25},
# {'lanes' : [LaneSpec(4, [0, 0])] *4,'width' :10, 'seed' : 25},
# {'lanes' : [LaneSpec(8, [0, 0])] *7,'width' :20, 'seed' : 25},
# {'lanes' : [LaneSpec(7, [0, 0])] *10,'width' :20, 'seed' : 125}]
### Sample test cases for Crossing Task
test_config = [{
'lanes': [LaneSpec(6, [-2, -2])] * 2 + [LaneSpec(6, [-5, -5])] * 2 +
[LaneSpec(5, [-4, -4])] * 2 + [LaneSpec(5, [-2, -2])] * 1,
'width':
30,
'seed':
101
}]
test_config = [{
'lanes': [LaneSpec(6, [-2, -2])] * 2 + [LaneSpec(4, [-3, -3])] * 2 +
[LaneSpec(6, [-4, -4])] * 2 + [LaneSpec(4, [-4, -4])] * 2 +
[LaneSpec(6, [-2, -2])] * 2 + [LaneSpec(4, [-3, -3])] * 2,
'width':
35,
'seed':
101
}]
import gym
from gym_grid_driving.envs.grid_driving import LaneSpec, Point
default_lanes = [LaneSpec(cars=7, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -1]),
LaneSpec(cars=6, speed_range=[-1, -1]),
LaneSpec(cars=6, speed_range=[-3, -1]),
LaneSpec(cars=7, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -1]),
LaneSpec(cars=6, speed_range=[-3, -2]),
LaneSpec(cars=7, speed_range=[-1, -1]),
LaneSpec(cars=6, speed_range=[-2, -1]),
LaneSpec(cars=8, speed_range=[-2, -2])]
default_speed_range = [-3, -1]
default_width = 50
def construct_curriculum_env(curr_id, tensor_state=True):
one_eight_config = {'agent_speed_range': default_speed_range, 'width': default_width,
'lanes': default_lanes,
'finish_position': Point(43, 8)
}
quarter_config = {'agent_speed_range': default_speed_range, 'width': default_width,
'lanes': default_lanes,
'finish_position': Point(36, 6)
}
half_config = {'agent_speed_range': default_speed_range, 'width': default_width,
'lanes': default_lanes,
'finish_position': Point(24, 4)
}
full_config = {'agent_speed_range': default_speed_range, 'width': default_width,
import gym
import gym_grid_driving
from gym_grid_driving.envs.grid_driving import LaneSpec, Point
import os
################### DO NOT CHANGE THIS ###################
if not SUBMISSION :
FAST_DOWNWARD_DIRECTORY_ABSOLUTE_PATH = "/fast_downward/"
else :
FAST_DOWNWARD_DIRECTORY_ABSOLUTE_PATH = ""
PDDL_FILE_ABSOLUTE_PATH = ""
##########################################################
### Sample test cases for Parking task.
test_config = [{'lanes' : [LaneSpec(2, [0, 0])] *3,'width' :5, 'seed' : 13},
{'lanes' : [LaneSpec(2, [0, 0])] *3,'width' :5, 'seed' : 10},
{'lanes' : [LaneSpec(3, [0, 0])] *4,'width' :10, 'seed' : 25},
{'lanes' : [LaneSpec(4, [0, 0])] *4,'width' :10, 'seed' : 25},
{'lanes' : [LaneSpec(8, [0, 0])] *7,'width' :20, 'seed' : 25},
{'lanes' : [LaneSpec(7, [0, 0])] *10,'width' :20, 'seed' : 125}]
test_case_number = 0 # Change the index for a different test case
LANES = test_config[test_case_number]['lanes']
WIDTH = test_config[test_case_number]['width']
RANDOM_SEED = test_config[test_case_number]['seed']
class GeneratePDDL_Stationary :
'''
def construct_task2_env(tensor_state=True):
large_config = {'agent_speed_range': [-3, -1], 'width': 50,
'lanes': default_lanes
}
small_config = {'observation_type': 'tensor', 'agent_speed_range': [-2, -1], 'stochasticity': 0.0, 'width': 10,
'lanes': [
LaneSpec(cars=3, speed_range=[-2, -1]),
LaneSpec(cars=4, speed_range=[-2, -1]),
LaneSpec(cars=2, speed_range=[-1, -1]),
LaneSpec(cars=2, speed_range=[-3, -1])
]}
medium_config = {'observation_type': 'tensor', 'agent_speed_range': [-3, -1], 'width': 15,
'lanes': [
LaneSpec(cars=3, speed_range=[-2, -1]),
LaneSpec(cars=4, speed_range=[-2, -1]),
LaneSpec(cars=2, speed_range=[-1, -1]),
LaneSpec(cars=2, speed_range=[-3, -1]),
LaneSpec(cars=3, speed_range=[-2, -1]),
LaneSpec(cars=4, speed_range=[-2, -1])
]}
medium_large_config = {'agent_speed_range': [-3, -1], 'width': 40,
'lanes': [LaneSpec(cars=6, speed_range=[-2, -1]),
LaneSpec(cars=7, speed_range=[-2, -1]),
LaneSpec(cars=5, speed_range=[-1, -1]),
LaneSpec(cars=5, speed_range=[-3, -1]),
LaneSpec(cars=6, speed_range=[-2, -1]),
LaneSpec(cars=7, speed_range=[-2, -1]),
]
}
curri_large_config = {'agent_speed_range': [-3, -1], 'width': 50,
'lanes': default_lanes,
'finish_position': Point(43, 6)
}
config = large_config
if tensor_state:
config['observation_type'] = 'tensor'
return gym.make('GridDriving-v0', **config)
math.sqrt(math.log(node.numVisits) / child.numVisits))
if val == bestValue:
bestNodes.append(child)
if val > bestValue:
bestNodes = [child]
bestValue = val
return random.choice(bestNodes)
if not SUBMISSION:
### Sample test cases.
test_config = [{
'lanes': [LaneSpec(1, [-1, -1])] * 3,
'width': 5,
'seed': 10,
'iters': 300
}, {
'lanes': [LaneSpec(2, [-2, -1])] * 3,
'width': 7,
'seed': 15,
'iters': 100
}, {
'lanes': [LaneSpec(2, [-2, -1])] * 4,
'width': 8,
'seed': 125,
'iters': 500
}, {
'lanes': [LaneSpec(2, [-3, -2])] * 4,
def getStateTuple(env):
'''
Helper function to convert an env state to a state feature vector.
'''
cars = env.cars
done = env.done
state = []
for car in cars:
state += [car.position.x, car.position.y]
state.append(int(done==True))
return state
if not SUBMISSION:
### Sample test cases.
test_config = [{'lanes' : [LaneSpec(0, [-2, -1])] *5,'width' :9, 'gamma' : 0.9, 'seed' : 15, 'fin_pos' : Point(0,0), 'agent_pos': Point(8,4),'stochasticity': 1. },
{'lanes' : [LaneSpec(1, [-2, -1])] *2,'width' :4, 'gamma' : 0.9, 'seed' : 15, 'fin_pos' : Point(0,1), 'agent_pos': Point(3,1),'stochasticity': 1. },
{'lanes' : [LaneSpec(1, [-3, -1])] *2 + [LaneSpec(0, [0, 0])],'width' :4, 'gamma' : 0.9, 'seed' : 100, 'fin_pos' : Point(0,0), 'agent_pos': Point(3,2),'stochasticity': .5 },
{'lanes' : [LaneSpec(0, [0, 0])] + [LaneSpec(1, [-3, -1])] *2,'width' :4, 'gamma' : 0.5, 'seed' : 128, 'fin_pos' : Point(0,0), 'agent_pos': Point(3,2),'stochasticity': 0.75 },
{'lanes' : [LaneSpec(1, [-3, -1])] *2 + [LaneSpec(0, [0, 0])],'width' :4, 'gamma' : 0.99, 'seed' : 111, 'fin_pos' : Point(0,0), 'agent_pos': Point(3,2),'stochasticity': .5 },
{'lanes' : [LaneSpec(1, [-3, -1]), LaneSpec(0, [0, 0]), LaneSpec(1, [-3, -1])] ,'width' :4, 'gamma' : 0.999, 'seed' : 125, 'fin_pos' : Point(0,0), 'agent_pos': Point(3,2),'stochasticity': 0.9 }]
test_case_number = 0 #Change the index for a different test case
LANES = test_config[test_case_number]['lanes']
WIDTH = test_config[test_case_number]['width']
RANDOM_SEED = test_config[test_case_number]['seed']
GAMMA = test_config[test_case_number]['gamma']
FIN_POS = test_config[test_case_number]['fin_pos']
AGENT_POS = test_config[test_case_number]['agent_pos']
stochasticity = test_config[test_case_number]['stochasticity']
env = gym.make('GridDriving-v0', lanes=LANES, width=WIDTH,
'''
val = (child.totalReward / child.numVisits) + (explorationValue * math.sqrt(math.log(node.numVisits) / child.numVisits))
if val == bestValue:
bestNodes.append(child)
if val > bestValue:
bestNodes = [child]
bestValue = val
return random.choice(bestNodes)
if not SUBMISSION:
### Sample test cases.
test_config = [{'lanes' : [LaneSpec(1, [-1, -1])] *3,'width' :5, 'seed' : 10, 'iters': 300},
{'lanes' : [LaneSpec(2, [-2, -1])] *3,'width' :7, 'seed' : 15, 'iters': 100},
{'lanes' : [LaneSpec(2, [-2, -1])] *4,'width' :8, 'seed' : 125, 'iters': 500},
{'lanes' : [LaneSpec(2, [-3, -2])] *4,'width' :10, 'seed' : 44, 'iters': 300},
{'lanes' : [LaneSpec(2, [-3, -1])] *4,'width' :10, 'seed' : 125, 'iters': 400},
{'lanes' : [LaneSpec(2, [-3, -1])] *4,'width' :10, 'seed' : 25, 'iters': 300}]
test_case_number = 5 #Change the index for a different test case
LANES = test_config[test_case_number]['lanes']
WIDTH = test_config[test_case_number]['width']
RANDOM_SEED = test_config[test_case_number]['seed']
numiters = test_config[test_case_number]['iters']
stochasticity = 1.
env = gym.make('GridDriving-v0', lanes=LANES, width=WIDTH,
agent_speed_range=(-3,-1), finish_position=Point(0,0), #agent_ pos_init=Point(4,2),
stochasticity=stochasticity, tensor_state=False, flicker_rate=0., mask=None, random_seed=RANDOM_SEED)
import gym
import gym_grid_driving
from gym_grid_driving.envs.grid_driving import LaneSpec, Point
import os
################### DO NOT CHANGE THIS ###################
if not SUBMISSION:
FAST_DOWNWARD_DIRECTORY_ABSOLUTE_PATH = "/fast_downward/"
else:
FAST_DOWNWARD_DIRECTORY_ABSOLUTE_PATH = ""
PDDL_FILE_ABSOLUTE_PATH = ""
##########################################################
### Sample test cases.
test_config = [{
'lanes': [LaneSpec(3, [-1, -1])] * 3,
'width': 5,
'seed': 12
}, {
'lanes': [LaneSpec(2, [-1, -1])] * 3,
'width': 5,
'seed': 25
}, {
'lanes': [LaneSpec(3, [-1, -1])] * 4,
'width': 10,
'seed': 125
}, {
'lanes': [LaneSpec(4, [-1, -1])] * 4,
'width': 10,
'seed': 28
}, {