gym是用來開發和比較強化學習演算法的工具包，在python中安裝gym函式庫和其中子場景都較為簡單。
安裝gym：
pip install gym
安裝自動駕駛模組，這裡使用Edouard Leurent 發佈在github 上的套件highway-env：
pip install --user git+https://github.com/eleurent/highway-env
其中包含6個場景：
#https://www.php.cn/link/c0fda89ebd645bd7cea60fcbb5960309
#設定環境安裝好後即可在程式碼中進行實驗（以高速公路場景為例）：
import gym
import highway_env
%matplotlib inline
env = gym.make('highway-v0')
env.reset()
for _ in range(3):
action = env.action_type.actions_indexes["IDLE"]
obs, reward, done, info = env.step(action)
env.render()
config =
{
"observation":
{
"type": "Kinematics",
#选取5辆车进行观察（包括ego vehicle）
"vehicles_count": 5,
#共7个特征
"features": ["presence", "x", "y", "vx", "vy", "cos_h", "sin_h"],
"features_range":
{
"x": [-100, 100],
"y": [-100, 100],
"vx": [-20, 20],
"vy": [-20, 20]
},
"absolute": False,
"order": "sorted"
},
"simulation_frequency": 8,# [Hz]
"policy_frequency": 2,# [Hz]
}
ACTIONS_ALL = {
0: 'LANE_LEFT',
1: 'IDLE',
2: 'LANE_RIGHT',
3: 'FASTER',
4: 'SLOWER'
}
import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.nn.functional as F
import torch.optim as optim
import torchvision.transforms as T
from torch import FloatTensor, LongTensor, ByteTensor
from collections import namedtuple
import random
Tensor = FloatTensor
EPSILON = 0# epsilon used for epsilon greedy approach
GAMMA = 0.9
TARGET_NETWORK_REPLACE_FREQ = 40 # How frequently target netowrk updates
MEMORY_CAPACITY = 100
BATCH_SIZE = 80
LR = 0.01 # learning rate
class DQNNet(nn.Module):
def __init__(self):
super(DQNNet,self).__init__()
self.linear1 = nn.Linear(35,35)
self.linear2 = nn.Linear(35,5)
def forward(self,s):
s=torch.FloatTensor(s)
s = s.view(s.size(0),1,35)
s = self.linear1(s)
s = self.linear2(s)
return s
class DQN(object):
def __init__(self):
self.net,self.target_net = DQNNet(),DQNNet()
self.learn_step_counter = 0
self.memory = []
self.position = 0
self.capacity = MEMORY_CAPACITY
self.optimizer = torch.optim.Adam(self.net.parameters(), lr=LR)
self.loss_func = nn.MSELoss()
def choose_action(self,s,e):
x=np.expand_dims(s, axis=0)
if np.random.uniform() < 1-e:
actions_value = self.net.forward(x)
action = torch.max(actions_value,-1)[1].data.numpy()
action = action.max()
else:
action = np.random.randint(0, 5)
return action
def push_memory(self, s, a, r, s_):
if len(self.memory) < self.capacity:
self.memory.append(None)
self.memory[self.position] = Transition(torch.unsqueeze(torch.FloatTensor(s), 0),torch.unsqueeze(torch.FloatTensor(s_), 0),
torch.from_numpy(np.array([a])),torch.from_numpy(np.array([r],dtype='float32')))#
self.position = (self.position + 1) % self.capacity
def get_sample(self,batch_size):
sample = random.sample(self.memory,batch_size)
return sample
def learn(self):
if self.learn_step_counter % TARGET_NETWORK_REPLACE_FREQ == 0:
self.target_net.load_state_dict(self.net.state_dict())
self.learn_step_counter += 1
transitions = self.get_sample(BATCH_SIZE)
batch = Transition(*zip(*transitions))
b_s = Variable(torch.cat(batch.state))
b_s_ = Variable(torch.cat(batch.next_state))
b_a = Variable(torch.cat(batch.action))
b_r = Variable(torch.cat(batch.reward))
q_eval = self.net.forward(b_s).squeeze(1).gather(1,b_a.unsqueeze(1).to(torch.int64))
q_next = self.target_net.forward(b_s_).detach() #
q_target = b_r + GAMMA * q_next.squeeze(1).max(1)[0].view(BATCH_SIZE, 1).t()
loss = self.loss_func(q_eval, q_target.t())
self.optimizer.zero_grad() # reset the gradient to zero
loss.backward()
self.optimizer.step() # execute back propagation for one step
return loss
Transition = namedtuple('Transition',('state', 'next_state','action', 'reward'))
import gym
import highway_env
from matplotlib import pyplot as plt
import numpy as np
import time
config =
{
"observation":
{
"type": "Kinematics",
"vehicles_count": 5,
"features": ["presence", "x", "y", "vx", "vy", "cos_h", "sin_h"],
"features_range":
{
"x": [-100, 100],
"y": [-100, 100],
"vx": [-20, 20],
"vy": [-20, 20]
},
"absolute": False,
"order": "sorted"
},
"simulation_frequency": 8,# [Hz]
"policy_frequency": 2,# [Hz]
}
env = gym.make("highway-v0")
env.configure(config)
dqn=DQN()
count=0
reward=[]
avg_reward=0
all_reward=[]
time_=[]
all_time=[]
collision_his=[]
all_collision=[]
while True:
done = False
start_time=time.time()
s = env.reset()
while not done:
e = np.exp(-count/300)#随机选择action的概率，随着训练次数增多逐渐降低
a = dqn.choose_action(s,e)
s_, r, done, info = env.step(a)
env.render()
dqn.push_memory(s, a, r, s_)
if ((dqn.position !=0)&(dqn.position % 99==0)):
loss_=dqn.learn()
count+=1
print('trained times:',count)
if (count%40==0):
avg_reward=np.mean(reward)
avg_time=np.mean(time_)
collision_rate=np.mean(collision_his)
all_reward.append(avg_reward)
all_time.append(avg_time)
all_collision.append(collision_rate)
plt.plot(all_reward)
plt.show()
plt.plot(all_time)
plt.show()
plt.plot(all_collision)
plt.show()
reward=[]
time_=[]
collision_his=[]
s = s_
reward.append(r)
end_time=time.time()
episode_time=end_time-start_time
time_.append(episode_time)
is_collision=1 if info['crashed']==True else 0
collision_his.append(is_collision)
以上是學習Python實現自動駕駛系統的詳細內容。更多資訊請關注PHP中文網其他相關文章！
