def play_episode(net, steps_in_episode):
env = helicopter.Helicopter(n_row=N_ROW,
n_col=N_COL,
p_fire=P_FIRE,
p_tree=P_TREE,
tree=TREE,
fire=FIRE,
empty=EMPTY)
obs = env.reset()
total_reward = 0.0
step_data = {}
episode_steps = []
episode_data = {}
for step_num in range(steps_in_episode):
grid, position = observations_to_tensors([obs])
action = get_action(grid, position, net)
next_obs, reward, is_done, info = env.step(action)
total_reward += reward
step_data['observation'] = obs
step_data['action'] = action
step_data['reward'] = reward
step_data['step_number'] = step_num
episode_steps.append(step_data)
obs = next_obs
step_data = {}
episode_data['total_reward'] = total_reward
episode_data['info'] = info
episode_data['all_steps'] = episode_steps
return episode_data
def load_stage(self, stage, demo=False): #, checkpoint=None):
"""Load a stage procedurally, or from a file. This method will import the named module, and load the class
within. The class must be named Stage<Name> where <Name> is the capitalized version of the module name."""
self.demo = demo
classname = "Stage%s" % stage.title()
module = __import__(stage)
class_obj = getattr(module, classname)
if not demo:
self.helicopter = helicopter.Helicopter(400,
400,
batch=self.sprite_batch,
context=self)
self.gunner = gunner.Gunner(400,
400,
batch=self.sprite_batch,
context=self)
self.rope = rope.Rope(length=ROPE_SEGMENTS,
anchor_start=self.helicopter,
anchor_end=self.gunner)
self.message("GET READY SOLDIER")
self.stage = class_obj(context=self)
# Zero out all of the bullets
self.bullets = []
self.bullet_pool = []
# Fill the bullet pool with dead bullet objects
for i in range(BULLET_POOL):
b = bullet.Bullet(x=0, y=0, batch=self.sprite_bullet_batch)
self.bullet_pool.append(b)
self.bullets.append(b)
if self.stage.music == None:
self.music_player = None
else:
self.music_player = pyglet.media.Player()
self.music_player.queue(self.stage.music)
self.music_player.eos_action = 'loop'
self.music_player.play()
#CORES
white = (255, 255, 255)
black = (0, 0, 0)
gray = (50, 50, 50)
red = (255, 0, 0)
green = (0, 255, 0)
blue = (0, 0, 255)
yellow = (255, 255, 0)
for convert_sprites in sprites.all_sprites:
convert_sprites.convert_alpha()
clock = pygame.time.Clock()
FPS = 30
player = helicopter.Helicopter(100, display_height / 2 - 40)
moving = True
godmode = False
#Pontos
score = 0
highscore_file = open('highscore.dat', "r")
highscore_int = int(highscore_file.read())
#NUVENS QUE PASSAM NO CENARIO
cloud_x = 800
cloud_y = random.randint(0, 400)
#VARIAVEIS DO INIMIGO
enemy_heli = enemy_heli.EnemyHeli(-100, display_height / 2 - 40)
enemy_heli_alive = False
# Environment parameters
N_ROW = 8
N_COL = 8
P_FIRE = 0.01
P_TREE = 0.30
# Symbols for cells
TREE = 3
FIRE = 7
EMPTY = 1
# Test environment to get some important attributes
env = helicopter.Helicopter(n_row=N_ROW,
n_col=N_COL,
p_fire=P_FIRE,
p_tree=P_TREE,
tree=TREE,
fire=FIRE,
empty=EMPTY)
N_ACTIONS = env.actions_cardinality
FREEZE_FRAMES = env.freeze
FOREST_ITERATIONS = 60
STEPS_PER_EPISODE = FREEZE_FRAMES * FOREST_ITERATIONS
EPOCHS = 1200
ITERATIONS = 2
BATCH_SIZE = 120
PERCENTILE = 90
CPUS = 1
# Take advantage of hardware if available
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.utils.tensorboard import SummaryWriter
import helicopter
N_ROW = 1
N_COL = 9
P_FIRE = 0.05
P_TREE = 0.30
ENV = helicopter.Helicopter(n_row=N_ROW,
n_col=N_COL,
p_fire=P_FIRE,
p_tree=P_TREE,
tree=0.30,
empty=0.10,
fire=0.70)
# Total time of the DQN iterations
EPOCHS = 800000
# Target network
# Synchronize target network each x steps
SYNC_TARGET = 2000
# Replay Memory
REPLAY_SIZE = 800000
# Start learning at this size of the replay memory
REPLAY_START_SIZE = 1000
FPSCLOCK = pygame.time.Clock()
FPS = 30
# background variables
background_width = 1920
# newLife variables
red_heart_x = 800
red_heart_y = random.randint(0, 400)
# main menu helicopter (for decoration only)
heli_main_x = 800
heli_main_y = random.randint(0, 400)
# player variables
player = helicopter.Helicopter(100, HALF_WINHEIGHT-40)
moving = True
# score variables
score = 0
hard_mode = 1800
highscore_file = open('highscore.dat', "r")
highscore_int = highscore_file.read() #high score in integer
# enemy helicopter variables
enemy_heli = enemy_heli.EnemyHeli(-100, HALF_WINHEIGHT-40)
enemy_heli_alive = False
# missile variables
missile_x = 800
missile_y = player.y
def load(self):
levels = self.get_levels()
if self.level_id > len(levels) - 1:
self.app.set_state(main.WIN)
self.app.score_manager.save()
else:
self.app.gui_manager.set_state(gui_manager.FADE_IN)
self.app.game_manager.clear_level()
self.level_name = levels[self.level_id]
self.app.gui_manager.update_times(
self.app.score_manager.run_scores.get(
util.get_filename(self.mode, self.level_name), 0),
self.app.score_manager.get_record(self.mode, self.level_name))
# map_data = levels.levels[self.level_id]()
if self.mode == 0:
directory = 'levels'
elif self.mode == 1:
directory = 'survival'
with open('{}/{}.dat'.format(directory, self.level_name),
'rb') as f:
map_data = pickle.load(f)
scene = self.app.renderer.scene
model_name, texture = map_data['terrain']
self.app.game_manager.terrain = terrain.Terrain(
self.app, model_name, texture)
scene.add(self.app.game_manager.terrain.canvas)
self.app.game_manager.player.spawn(map_data['spawn_pos'])
if self.mode == 0:
self.app.game_manager.goal.spawn(map_data['goal_pos'])
elif self.mode == 1:
self.app.game_manager.goal.despawn()
for data in map_data['buildings']:
b = building.Building(self.app,
building.Building.data[data[0]],
data[1:4], data[4])
# b = building.Building(self.app, building.Building.data[data[0]], data[1:4], 0)
self.app.game_manager.game_objects.add(b)
scene.add(b.canvas)
for data in map_data['platforms']:
if data[0] == 0:
platform.Hedge(self.app, data[1:4])
elif data[0] == 1:
platform.InvisiblePlatform(self.app, data[1:4])
elif data[0] == 2:
platform.LavaPlatform(self.app, data[1:4])
elif data[0] == 3:
platform.Trampoline(self.app, data[1:4])
for data in map_data['elevators']:
e = elevator.Elevator(self.app, data[1:4], data[4])
self.app.game_manager.game_objects.add(e) # spawn later
scene.add(e.canvas)
for data in map_data['powerups']:
if data[0] == 0:
e = powerup.Fuel(self.app, data[1:4])
self.app.game_manager.game_objects.add(e) # spawn later
scene.add(e.canvas)
elif data[0] == 1:
e = powerup.Health(self.app, data[1:4])
self.app.game_manager.game_objects.add(e) # spawn later
scene.add(e.canvas)
elif data[0] == 2:
e = powerup.SlowTime(self.app, data[1:4])
self.app.game_manager.game_objects.add(e) # spawn later
scene.add(e.canvas)
for data in map_data['vehicles']:
if data[0] == 0:
v = car.Car(self.app)
elif data[0] == 1:
v = helicopter.Helicopter(self.app)
v.spawn(data[1:4])
for data in map_data['enemies']:
if data[0] == 0:
enemy.Turret(self.app, data[1:4])
elif data[0] == 1:
enemy.Bee(self.app, data[1:4])
elif data[0] == 2:
enemy.BowlSpawner(self.app, data[1:4])
elif data[0] == 3:
enemy.InvisibleEnemy(self.app, data[1:4])
self.app.game_manager.set_state(self.mode)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Feb 26 18:17:54 2020
@author: ebecerra
"""
import helicopter
import numpy as np
env = helicopter.Helicopter(n_row = 8, n_col = 8,
tree = 3,
fire = 7,
empty = 1, p_fire = 0.01, p_tree = 0.3)
# First observation
observation = env.reset()
env.render()
total_reward = 0
for i in range(env.freeze * 100):
print('.', end='')
action = np.random.choice(list(env.actions_set))
observation, reward, done, info = env.step(action)
total_reward += reward
env.render()
print('\nTotal Reward: {}'.format(total_reward))
np.random.choice(env.actions_set)
