使用PPO算法玩“超级马里奥兄弟”
【摘要】 在此教程中，我们利用PPO算法来玩“Super Mario Bros”（超级马里奥兄弟）。目前来看，对于绝大部分关卡，智能体都可以在1500个episode内学会过关，您可以在超参数栏输入您想要的游戏关卡和训练算法超参数。
实验目标
通过本案例的学习和课后作业的练习：
- 了解PPO算法的基本概念
- 了解如何基于PPO训练一个小游戏
- 了解强化学习训练推理游戏的整体流程
你也可以将本案例相关的 ipynb 学习笔记分享到 AI Gallery Notebook 版块获得成长值，分享方法请查看此文档。
在此教程中，我们利用PPO算法来玩“Super Mario Bros”（超级马里奥兄弟）。目前来看，对于绝大部分关卡，智能体都可以在1500个episode内学会过关，您可以在超参数栏输入您想要的游戏关卡和训练算法超参数。
整体流程：创建马里奥环境->构建PPO算法->训练->推理->可视化效果
注意事项
-
本案例运行环境为 Pytorch-1.0.0，且需使用 GPU 运行，请查看《ModelAtrs JupyterLab 硬件规格使用指南》了解切换硬件规格的方法；
-
如果您是第一次使用 JupyterLab，请查看《ModelAtrs JupyterLab使用指导》了解使用方法；
-
如果您在使用 JupyterLab 过程中碰到报错，请参考《ModelAtrs JupyterLab常见问题解决办法》尝试解决问题。
1. 程序初始化
第1步：安装基础依赖
!pip install -U pip
!pip install gym==0.19.0
!pip install tqdm==4.48.0
!pip install nes-py==8.1.0
!pip install gym-super-mario-bros==7.3.2import os
import shutil
import subprocess as sp
from collections import deque
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.multiprocessing as _mp
from torch.distributions import Categorical
import torch.multiprocessing as mp
from nes_py.wrappers import JoypadSpace
import gym_super_mario_bros
from gym.spaces import Box
from gym import Wrapper
from gym_super_mario_bros.actions import SIMPLE_MOVEMENT, COMPLEX_MOVEMENT, RIGHT_ONLY
import cv2
import matplotlib.pyplot as plt
from IPython import display
import moxing as mox2. 训练参数初始化
该部分参数可以自己调整，以训练出更好的效果
opt={
"world": 1, # 可选大关：1,2,3,4,5,6,7,8
"stage": 1, # 可选小关：1,2,3,4
"action_type": "simple", # 动作类别："simple"，"right_only", "complex"
'lr': 1e-4, # 建议学习率：1e-3，1e-4, 1e-5，7e-5
'gamma': 0.9, # 奖励折扣
'tau': 1.0, # GAE参数
'beta': 0.01, # 熵系数
'epsilon': 0.2, # PPO的Clip系数
'batch_size': 16, # 经验回放的batch_size
'max_episode':10, # 最大训练局数
'num_epochs': 10, # 每条经验回放次数
"num_local_steps": 512, # 每局的最大步数
"num_processes": 8, # 训练进程数，一般等于训练机核心数
"save_interval": 5, # 每{}局保存一次模型
"log_path": "./log", # 日志保存路径
"saved_path": "./model", # 训练模型保存路径
"pretrain_model": True, # 是否加载预训练模型，目前只提供1-1关卡的预训练模型，其他需要从零开始训练
"episode":5
}3. 创建环境
结束标志：
-
胜利：mario到达本关终点
-
失败：mario受到敌人的伤害、坠入悬崖或者时间用完
奖励函数：
-
得分：收集金币、踩扁敌人、结束时夺旗
-
扣分：受到敌人伤害、掉落悬崖、结束时未夺旗
# 创建环境
def create_train_env(world, stage, actions, output_path=None):
# 创建基础环境
env = gym_super_mario_bros.make("SuperMarioBros-{}-{}-v0".format(world, stage))
env = JoypadSpace(env, actions)
# 对环境自定义
env = CustomReward(env, world, stage, monitor=None)
env = CustomSkipFrame(env)
return env
# 对原始环境进行修改，以获得更好的训练效果
class CustomReward(Wrapper):
def __init__(self, env=None, world=None, stage=None, monitor=None):
super(CustomReward, self).__init__(env)
self.observation_space = Box(low=0, high=255, shape=(1, 84, 84))
self.curr_score = 0
self.current_x = 40
self.world = world
self.stage = stage
if monitor:
self.monitor = monitor
else:
self.monitor = None
def step(self, action):
state, reward, done, info = self.env.step(action)
if self.monitor:
self.monitor.record(state)
state = process_frame(state)
reward += (info["score"] - self.curr_score) / 40.
self.curr_score = info["score"]
if done:
if info["flag_get"]:
reward += 50
else:
reward -= 50
if self.world == 7 and self.stage == 4:
if (506 <= info["x_pos"] <= 832 and info["y_pos"] > 127) or (
832 < info["x_pos"] <= 1064 and info["y_pos"] < 80) or (
1113 < info["x_pos"] <= 1464 and info["y_pos"] < 191) or (
1579 < info["x_pos"] <= 1943 and info["y_pos"] < 191) or (
1946 < info["x_pos"] <= 1964 and info["y_pos"] >= 191) or (
1984 < info["x_pos"] <= 2060 and (info["y_pos"] >= 191 or info["y_pos"] < 127)) or (
2114 < info["x_pos"] < 2440 and info["y_pos"] < 191) or info["x_pos"] < self.current_x - 500:
reward -= 50
done = True
if self.world == 4 and self.stage == 4:
if (info["x_pos"] <= 1500 and info["y_pos"] < 127) or (
1588 <= info["x_pos"] < 2380 and info["y_pos"] >= 127):
reward = -50
done = True
self.current_x = info["x_pos"]
return state, reward / 10., done, info
def reset(self):
self.curr_score = 0
self.current_x = 40
return process_frame(self.env.reset())
class MultipleEnvironments:
def __init__(self, world, stage, action_type, num_envs, output_path=None):
self.agent_conns, self.env_conns = zip(*[mp.Pipe() for _ in range(num_envs)])
if action_type == "right_only":
actions = RIGHT_ONLY
elif action_type == "simple":
actions = SIMPLE_MOVEMENT
else:
actions = COMPLEX_MOVEMENT
self.envs = [create_train_env(world, stage, actions, output_path=output_path) for _ in range(num_envs)]
self.num_states = self.envs[0].observation_space.shape[0]
self.num_actions = len(actions)
for index in range(num_envs):
process = mp.Process(target=self.run, args=(index,))
process.start()
self.env_conns[index].close()
def run(self, index):
self.agent_conns[index].close()
while True:
request, action = self.env_conns[index].recv()
if request == "step":
self.env_conns[index].send(self.envs[index].step(action.item()))
elif request == "reset":
self.env_conns[index].send(self.envs[index].reset())
else:
raise NotImplementedError
def process_frame(frame):
if frame is not None:
frame = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
frame = cv2.resize(frame, (84, 84))[None, :, :] / 255.
return frame
else:
return np.zeros((1, 84, 84))
class CustomSkipFrame(Wrapper):
def __init__(self, env, skip=4):
super(CustomSkipFrame, self).__init__(env)
self.observation_space = Box(low=0, high=255, shape=(skip, 84, 84))
self.skip = skip
self.states = np.zeros((skip, 84, 84), dtype=np.float32)
def step(self, action):
total_reward = 0
last_states = []
for i in range(self.skip):
state, reward, done, info = self.env.step(action)
total_reward += reward
if i >= self.skip / 2:
last_states.append(state)
if done:
self.reset()
return self.states[None, :, :, :].astype(np.float32), total_reward, done, info
max_state = np.max(np.concatenate(last_states, 0), 0)
self.states[:-1] = self.states[1:]
self.states[-1] = max_state
return self.states[None, :, :, :].astype(np.float32), total_reward, done, info
def reset(self):
state = self.env.reset()
self.states = np.concatenate([state for _ in range(self.skip)], 0)
return self.states[None, :, :, :].astype(np.float32)4. 定义神经网络
神经网络结构包含四层卷积网络和一层全连接网络，提取的特征输入critic层和actor层，分别输出value值和动作概率分布。
class Net(nn.Module):
def __init__(self, num_inputs, num_actions):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(num_inputs, 32, 3, stride=2, padding=1)
self.conv2 = nn.Conv2d(32, 32, 3, stride=2, padding=1)
self.conv3 = nn.Conv2d(32, 32, 3, stride=2, padding=1)
self.conv4 = nn.Conv2d(32, 32, 3, stride=2, padding=1)
self.linear = nn.Linear(32 * 6 * 6, 512)
self.critic_linear = nn.Linear(512, 1)
self.actor_linear = nn.Linear(512, num_actions)
self._initialize_weights()
def _initialize_weights(self):
for module in self.modules():
if isinstance(module, nn.Conv2d) or isinstance(module, nn.Linear):
nn.init.orthogonal_(module.weight, nn.init.calculate_gain('relu'))
nn.init.constant_(module.bias, 0)
def forward(self, x):
x = F.relu(self.conv1(x))
x = F.relu(self.conv2(x))
x = F.relu(self.conv3(x))
x = F.relu(self.conv4(x))
x = self.linear(x.view(x.size(0), -1))
return self.actor_linear(x), self.critic_linear(x)6. 训练模型
训练10 Episode，耗时约5分钟
train(opt)加载预训练模型
Episode: 1. Total loss: 1.1230244636535645
Episode: 2. Total loss: 2.553663730621338
Episode: 3. Total loss: 1.768389344215393
Episode: 4. Total loss: 1.6962862014770508
Episode: 5. Total loss: 1.0912611484527588
Episode: 6. Total loss: 1.6626232862472534
Episode: 7. Total loss: 1.9952025413513184
Episode: 8. Total loss: 1.2410558462142944
Episode: 9. Total loss: 1.3711413145065308
Episode: 10. Total loss: 1.21552050113677987. 使用模型推理游戏
定义推理函数
def infer(opt):
if torch.cuda.is_available():
torch.cuda.manual_seed(123)
else:
torch.manual_seed(123)
if opt['action_type'] == "right":
actions = RIGHT_ONLY
elif opt['action_type'] == "simple":
actions = SIMPLE_MOVEMENT
else:
actions = COMPLEX_MOVEMENT
env = create_train_env(opt['world'], opt['stage'], actions)
model = Net(env.observation_space.shape[0], len(actions))
if torch.cuda.is_available():
model.load_state_dict(torch.load("{}/ppo_super_mario_bros_{}_{}_{}".format(opt['saved_path'],opt['world'], opt['stage'],opt['episode'])))
model.cuda()
else:
model.load_state_dict(torch.load("{}/ppo_super_mario_bros_{}_{}_{}".format(opt['saved_path'], opt['world'], opt['stage'],opt['episode']),
map_location=torch.device('cpu')))
model.eval()
state = torch.from_numpy(env.reset())
plt.figure(figsize=(10,10))
img = plt.imshow(env.render(mode='rgb_array'))
while True:
if torch.cuda.is_available():
state = state.cuda()
logits, value = model(state)
policy = F.softmax(logits, dim=1)
action = torch.argmax(policy).item()
state, reward, done, info = env.step(action)
state = torch.from_numpy(state)
img.set_data(env.render(mode='rgb_array')) # just update the data
display.display(plt.gcf())
display.clear_output(wait=True)
if info["flag_get"]:
print("World {} stage {} completed".format(opt['world'], opt['stage']))
break
if done and info["flag_get"] is False:
print('Game Failed')
breakinfer(opt)
8. 作业¶
【版权声明】本文为华为云社区用户原创内容，转载时必须标注文章的来源（华为云社区）、文章链接、文章作者等基本信息， 否则作者和本社区有权追究责任。如果您发现本社区中有涉嫌抄袭的内容，欢迎发送邮件进行举报，并提供相关证据，一经查实，本社区将立刻删除涉嫌侵权内容，举报邮箱：
cloudbbs@huaweicloud.com
- 点赞
- 收藏
- 关注作者
评论（0）