gpt4 book ai didi

python - OpenAI 将自定义游戏集成到健身房环境中

转载 作者:太空宇宙 更新时间:2023-11-03 10:22:15 25 4
gpt4 key购买 nike

[简介]我是 OpenAI 的初学者,我制作了一个自定义游戏,我想在其中实现一个自学习代理。我关注了this guide在 GitHub 上设置存储库,但是我不明白如何格式化我的代码以使用gym-foo/gym_foo/envs/foo_env.py的内容

[问题]是否有人可以指导我如何构建我的代码,使其与以下内容兼容:

class FooEnv(gym.Env):
metadata = {'render.modes': ['human']}

def __init__(self):
...
def step(self, action):
...
def reset(self):
...
def render(self, mode='human', close=False):
...

[代码]

import pygame
import time
import random
from pygame.locals import *

pygame.init()

display_width = 1002
display_height = 720

black = (0,0,0)
white = (255,255,255)
red = (220,0,0)
blue = (53,155,255)
green = (0,190,0)
bright_red = (255,0,0)
bright_green = (0,255,0)
dark_blue = (0,102,204)
yellow = (255, 255, 0)

gameDisplay = pygame.display.set_mode((display_width,display_height)) #creates surface/ display
pygame.display.set_caption('Blob Arena') #name of project
clock = pygame.time.Clock() #sets a clock

#________________________________________________________________________________________

blobImage = pygame.image.load('blob2.png')
blobIcon = pygame.image.load('blob_img.png')
bulletpicture = pygame.image.load("bullet.png")
pygame.display.set_icon(blobIcon)
pause = True
blob_width = 51
blob_height = 51
bullet_width = 12
bullet_height = 5

bullets=[]
bullets2=[]

def blob(x,y):
gameDisplay.blit(blobImage,(x,y)) #drawing to background

def bullets_hit(count):
font = pygame.font.SysFont(None, 25)
text = font.render("Score: "+str(count), True, black)
gameDisplay.blit(text,(0,20))

def player_lives(count):
font = pygame.font.SysFont(None, 25)
text = font.render("Lives Left: "+str(count), True, bright_red)
gameDisplay.blit(text,(0,0))

def game_intro():
intro = True
while intro:
for event in pygame.event.get():
if event.type == pygame.QUIT:
pygame.quit()
quit()

gameDisplay.fill(dark_blue)
largeText = pygame.font.Font('freesansbold.ttf', 110)
TextSurf, TextRect = text_objects("Blob Arena", largeText) # Returns text surface and rectangle
TextRect.center = ((display_width / 2), (display_height / 2.5))
gameDisplay.blit(TextSurf, TextRect)
button("Training 1", 200, 430, 140, 53, green, bright_green, game_loop)
button("Training 2", 431, 430, 140, 53, green, bright_green, game_loop)
button("Training 3", 662, 430, 140, 53, green, bright_green, game_loop)
button("Human vs AI", 315.5, 550, 140, 53, green, bright_green, game_loop)
button("Quit", 546.5, 550, 140, 53, red, bright_red, quit_game)

pygame.display.update()
clock.tick(15)

def button(msg,x,y,w,h,ic,ac,action=None):
mouse = pygame.mouse.get_pos()
click = pygame.mouse.get_pressed() #collects mouse left, right and middle button
if x + w > mouse[0] > x and y + h > mouse[1] > y:
pygame.draw.rect(gameDisplay, ac, (x, y, w, h))
if click[0] == 1 and action!= None:
action()
else:
pygame.draw.rect(gameDisplay, ic, (x, y, w, h))

smallText = pygame.font.Font("freesansbold.ttf", 20)
textSurf, textRect = text_objects(msg, smallText)
textRect.center = ((x + (w / 2)), (y + (h / 2)))
gameDisplay.blit(textSurf, textRect)

def unpause():
global pause
pause = False

def paused():
largeText = pygame.font.Font('freesansbold.ttf', 110)
TextSurf, TextRect = text_objects("Paused", largeText) # Returns text surface and rectangle
TextRect.center = ((display_width / 2), (display_height / 2.5))
gameDisplay.blit(TextSurf, TextRect)

while pause:
for event in pygame.event.get():
if event.type == pygame.QUIT:
pygame.quit()
quit()

button("Continue", 315.5, 450, 140, 53, green, bright_green, unpause)
button("Quit", 546.5, 450, 140, 53, red, bright_red, quit_game)

pygame.display.update()
clock.tick(15)

def text_objects(text, font):
textSurface = font.render(text, True, black)
return textSurface, textSurface.get_rect()

def quit_game():
pygame.quit()
quit()

def game_over():
largeText = pygame.font.Font('freesansbold.ttf', 110)
TextSurf, TextRect = text_objects("Game Over", largeText) # Returns text surface and rectangle
TextRect.center = ((display_width / 2), (display_height / 2.5))
gameDisplay.blit(TextSurf, TextRect)

while True:
for event in pygame.event.get():
if event.type == pygame.QUIT:
pygame.quit()
quit()

button("Play Again", 280.5, 450, 140, 53, green, bright_green,game_loop)
button("Quit", 581.5, 450, 140, 53, red, bright_red,quit_game)

pygame.display.update()
clock.tick(15)

def game_loop():
global pause
x = (display_width * 0.08)
y = (display_height * 0.2)

x_change = 0
y_change = 0

blob_speed = 2

velocity = [2, 2]

score = 0
lives = 3

pos_x = display_width/1.2
pos_y = display_height/1.2

previous_time = pygame.time.get_ticks()
previous_time2 = pygame.time.get_ticks()

gameExit = False
while not gameExit:
for event in pygame.event.get():#monitors hardware movement/ clicks
if event.type == pygame.QUIT:
pygame.quit()
quit()

pos_x += velocity[0]
pos_y += velocity[1]

if pos_x + blob_width > display_width or pos_x < 601:
velocity[0] = -velocity[0]

if pos_y + blob_height > display_height or pos_y < 0:
velocity[1] = -velocity[1]

for b in range(len(bullets2)):
bullets2[b][0] -= 6

for bullet in bullets2:
if bullet[0] < 0:
bullets2.remove(bullet)


current_time2 = pygame.time.get_ticks()
#ready to fire when 500 ms have passed.
if current_time2 - previous_time2 > 500:
previous_time2 = current_time2
bullets2.append([pos_x+25, pos_y+24])

# Checks to see if any keys are held down and remembers them with the variable keys.
keys = pygame.key.get_pressed()

for b in range(len(bullets)):
bullets[b][0] += 6

for bullet in bullets:
if bullet[0] > 1005:
bullets.remove(bullet)

if keys[pygame.K_SPACE]:
current_time = pygame.time.get_ticks()
#ready to fire when 500 ms have passed.
if current_time - previous_time > 500:
previous_time = current_time
bullets.append([x+25, y+24])

# If the player is holding down one key or the other the blob moves in that direction
if x < 0:
x = 0
if keys[pygame.K_a]:
x_change = -blob_speed
if x > 401 - blob_width:
x = 401 - blob_width
if keys[pygame.K_d]:
x_change = blob_speed
if keys[pygame.K_p]:
pause = True
paused()


# If the player is holding down both or neither of the keys the blob stops
if keys[pygame.K_a] and keys[pygame.K_d]:
x_change = 0
if not keys[pygame.K_a] and not keys[pygame.K_d]:
x_change = 0

if y < 0:
y = 0
if keys[pygame.K_w]:
y_change = -blob_speed
if y > display_height - blob_height:
y = display_height - blob_height
if keys[pygame.K_s]:
y_change = blob_speed


if keys[pygame.K_w] and keys[pygame.K_s]:
y_change = 0
if not keys[pygame.K_w] and not keys[pygame.K_s]:
y_change = 0


#print(event)
# Reset x and y to new position
x += x_change
y += y_change

gameDisplay.fill(blue) #changes background surface
bullets_hit(score)
player_lives(lives)
pygame.draw.line(gameDisplay, black, (601, display_height), (601, 0), 3)
pygame.draw.line(gameDisplay, black, (401, display_height), (401, 0), 3)
blob(pos_x, pos_y)
blob(x, y)

for bullet in bullets:
gameDisplay.blit(bulletpicture, pygame.Rect(bullet[0], bullet[1], 0, 0))
if bullet[0] > pos_x and bullet[0] < pos_x + blob_width:
if bullet[1] > pos_y and bullet[1] < pos_y + blob_height or bullet[1] + bullet_height > pos_y and bullet[1] + bullet_height < pos_y + blob_height:
bullets.remove(bullet)
score+=1

for bullet in bullets2:
gameDisplay.blit(bulletpicture, pygame.Rect(bullet[0], bullet[1], 0, 0))
if bullet[0] + bullet_width < x + blob_width and bullet[0] > x:
if bullet[1] > y and bullet[1] < y + blob_height or bullet[1] + bullet_height > y and bullet[1] + bullet_height < y + blob_height:
bullets2.remove(bullet)
lives-=1

if lives == 0:
game_over()


pygame.display.update() #update screen
clock.tick(120)#moves frame on (fps in parameters)

game_intro()
game_loop()
pygame.quit()
quit()

[其他信息]我将使用 https://github.com/Hvass-Labs/TensorFlow-Tutorials/blob/master/reinforcement_learning.py 中的强化学习算法据我了解,需要有一个gym环境才能让gym.make()工作。任何帮助将不胜感激,如果需要更多信息,请告诉我。

最佳答案

我没有使用 pygame 库的经验,也不了解其内部工作原理,这可能会对哪些代码需要在哪里运行产生一些影响,所以我不能 100% 确定所有那。但是,最好从一些直观的理解开始,大致了解应该在哪里发生的事情:

  • __init__() 应该运行任何一次性设置。我可以想象像 pygame.init() 这样的东西可能必须放在这里,但我不能 100% 确定,因为我不熟悉 pygame
  • 每当代理选择一个 Action 时,就应该调用
  • step(),然后运行游戏的单个“帧”,根据代理选择的 Action 将其向前移动。或者,如果您的游戏中单个 Action 需要多个帧,则应在此处运行多个帧。本质上:让游戏继续前进,直到到达代理应该再次选择新 Action 的点,然后返回当前的游戏状态。
  • reset() 应该...好吧,重置游戏。因此,恢复到(或随机的,无论你想要什么)初始游戏状态,运行可能需要的任何清理。例如,我也可以想象 pygame.init() 属于这里。这取决于该函数到底做什么。如果只需要运行一次,则属于__init__()。如果它需要在每个新游戏/“剧集”开始时运行,则 ir 属于 reset()
  • render() 可能应该包含大部分与图形相关的代码。例如,您可以尝试从 cartpole environment 中获取灵感。在gym中,这里也绘制了一些相当简单的图形。看起来它应该恰好绘制一帧。
<小时/>

现在,看看您开始的代码,似乎有大量的用户界面代码...与按钮、暂停/取消暂停、花哨的(动画?)介绍相关的各种代码比赛开始。不知道你是否有能力摆脱这一切?如果您纯粹进行强化学习,那么您可能可以。如果您仍然需要用户交互,则可能不能,然后事情就会变得更加困难,因为所有这些事情都不能很好地适应 gym 框架。

我可以尝试对代码的剩余部分及其应该去的位置进行一些有根据的猜测,但无论如何,您都应该根据上面更一般的准则仔细检查所有内容:

def reset(self):
# all the following code seems to define the initial game state
x = (display_width * 0.08)
y = (display_height * 0.2)

x_change = 0
y_change = 0

blob_speed = 2

velocity = [2, 2]

score = 0
lives = 3

pos_x = display_width/1.2
pos_y = display_height/1.2

bullets=[]
bullets2=[]

step() 可能应该包含 game_loop()while 循环中的大部分代码。不过,应该修改按键输入检查代码,而是应该开始使用传递到 step() 中的 action。最后,step() 预计返回一个包含以下内容的元组:

  • 下一个游戏状态,代理可以用来决定下一步的行动。如果您愿意,这可以是原始像素,也可以是更容易学习的东西(例如告诉您事物在哪里的一堆功能)。
  • 奖励,表明您的代理行动有多好。
  • True 如果游戏现在结束,False 否则。
  • 一些字典,包含您喜欢的任何额外信息,用于调试目的。可以简单地是一个空字典{}

关于python - OpenAI 将自定义游戏集成到健身房环境中,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/49637378/

25 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com