【六】强化学习之DQN---PaddlePaddlle【PARL】框架｛飞桨｝

#加载库
import paddle.fluid as fluid
import numpy as np
#生成数据
np.random.seed(0)
outputs = np.random.randint(5, size=(10, 4))
res = []
for i in range(10):
        # 假设方程式为 y=4a+6b+7c+2d
        y = 4*outputs[i][0]+6*outputs[i][1]+7*outputs[i][2]+2*outputs[i][3]
        res.append([y])
# 定义数据
train_data=np.array(outputs).astype('float32')
y_true = np.array(res).astype('float32')

#定义网络
x = fluid.layers.data(name="x",shape=[4],dtype='float32')
y = fluid.layers.data(name="y",shape=[1],dtype='float32')
y_predict = fluid.layers.fc(input=x,size=1,act=None)
#定义损失函数
cost = fluid.layers.square_error_cost(input=y_predict,label=y)
avg_cost = fluid.layers.mean(cost)
#定义优化方法
sgd_optimizer = fluid.optimizer.SGD(learning_rate=0.05)
sgd_optimizer.minimize(avg_cost)
#参数初始化
cpu = fluid.CPUPlace()
exe = fluid.Executor(cpu)
exe.run(fluid.default_startup_program())
##开始训练，迭代500次
for i in range(500):
        outs = exe.run(
                feed={'x':train_data,'y':y_true},
                fetch_list=[y_predict.name,avg_cost.name])
        if i%50==0:
                print ('iter={:.0f},cost={}'.format(i,outs[1][0]))
#存储训练结果
params_dirname = "result"
fluid.io.save_inference_model(params_dirname, ['x'], [y_predict], exe)

# 开始预测
infer_exe = fluid.Executor(cpu)
inference_scope = fluid.Scope()
# 加载训练好的模型
with fluid.scope_guard(inference_scope):
        [inference_program, feed_target_names,
         fetch_targets] = fluid.io.load_inference_model(params_dirname, infer_exe)

# 生成测试数据
test = np.array([[[9],[5],[2],[10]]]).astype('float32')
# 进行预测
results = infer_exe.run(inference_program,
                                                feed={"x": test},
                                                fetch_list=fetch_targets)
# 给出题目为 【9,5,2,10】 输出y=4*9+6*5+7*2+10*2的值
print ("9a+5b+2c+10d={}".format(results[0][0]))

 import random
import collections   #导入队列库，可以定义经验池队列
import numpy as np
 
 
class ReplayMemory(object):
    def __init__(self, max_size):
        self.buffer = collections.deque(maxlen=max_size)  #长度就是经验池容量
 
    def append(self, exp):
        self.buffer.append(exp)#增加一条经验（obs, action, reward, next_obs, done ）
    def sample(self, batch_size):
        mini_batch = random.sample(self.buffer, batch_size)
        obs_batch, action_batch, reward_batch, next_obs_batch, done_batch = [], [], [], [], []
 
        for experience in mini_batch:          #每一条batch分解一下，加到对应数组里
            s, a, r, s_p, done = experience
            obs_batch.append(s)
            action_batch.append(a)
            reward_batch.append(r)
            next_obs_batch.append(s_p)
            done_batch.append(done)
 
        return np.array(obs_batch).astype('float32'), \
            np.array(action_batch).astype('float32'), np.array(reward_batch).astype('float32'),\
            np.array(next_obs_batch).astype('float32'), np.array(done_batch).astype('float32')
 
    def __len__(self):
        return len(self.buffer)
 

with fluid.program_guard(self.pred_program):  # 搭建计算图用于 预测动作，定义输入输出变量
            obs = layers.data(
                name='obs', shape=[self.obs_dim], dtype='float32')
            self.value = self.alg.predict(obs)