PyTorch学习（14）——强化学习（DQN）

强化学习（Deep Q Network， DQN）是一种融合了神经网络和Q learning的方法。实现不经过supervision，让机器学会做某件事情（如AlphaGo）。

两种使得DQN变得很强大的因素：

1、Experience replay：随机抽取以前的经历进行学习

2、Fixed Q-targets：

接下来，将介绍如何在PyTorch中使用强化学习DQN。

接下来将实现gym模块中让机器人自己学会将杆子立起来。

示例代码：

import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
from torch.autograd import Variable
import gym

# 超参数
BATCH_SIZE = 32
LR = 0.01  # learning rate
# 强化学习的参数
EPSILON = 0.9  # greedy policy
GAMMA = 0.9  # reward discount
TARGET_REPLACE_ITER = 100  # target update frequency
MEMORY_CAPACITY = 2000
# 导入实验环境
env = gym.make('CartPole-v0')
env = env.unwrapped
N_ACTIONS = env.action_space.n
N_STATES = env.observation_space.shape[0]


class Net(nn.Module):
    def __init__(self, ):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(N_STATES, 10)
        self.fc1.weight.data.normal_(0, 0.1)  # 初始化
        self.out = nn.Linear(10, N_ACTIONS)
        self.out.weight.data.normal_(0, 0.1)  # 初始化

    def forward(self, x):
        x = self.fc1(x)
        x = F.relu(x)
        actions_value = self.out(x)
        return actions_value

class DQN(object):
    def __init__(self):
        self.eval_net, self.target_net = Net(), Net()
        # 记录学习到多少步
        self.learn_step_counter = 0  # for target update
        self.memory_counter = 0  # for storing memory
        # 初始化memory
        self.memory = np.zeros((MEMORY_CAPACITY, N_STATES * 2 + 2))
        self.optimizer = torch.optim.Adam(self.eval_net.parameters(), lr=LR)
        self.loss_func = nn.MSELoss()

    def choose_action(self, x):
        x = Variable(torch.unsqueeze(torch.FloatTensor(x), 0))
        if np.random.uniform() < EPSILON:
            action_value = self.eval_net.forward(x)
            action = torch.max(action_value, 1)[1].data.numpy()[0, 0]
        else: # random
            action = np.random.randint(0, N_ACTIONS)
        return action

    # s:当前状态， a:动作, r:reward奖励, s_:下一步状态
    def store_transaction(self, s, a, r, s_):
        transaction = np.hstack((s, [a, r], s_))
        # replace the old memory with new memory
        index = self.memory_counter % MEMORY_CAPACITY
        self.memory[index, :] = transaction
        self.memory_counter += 1

    def learn(self):
        # target net update
        if self.learn_step_counter % TARGET_REPLACE_ITER == 0:
            self.target_net.load_state_dict(self.eval_net.state_dict())

        sample_index = np.random.choice(MEMORY_CAPACITY, BATCH_SIZE)
        b_memory = self.memory[sample_index, :]
        b_s = Variable(torch.FloatTensor(b_memory[:, :N_STATES]))
        b_a = Variable(torch.LongTensor(b_memory[:, N_STATES: N_STATES+1].astype(int)))
        b_r = Variable(torch.FloatTensor(b_memory[:, N_STATES + 1: N_STATES+2]))
        b_s_ = Variable(torch.FloatTensor(b_memory[:, -N_STATES: ]))

        q_eval = self.eval_net(b_s).gather(1, b_a)
        q_next = self.target_net(b_s_).detach()
        q_target = b_r + GAMMA * q_next.max(1)[0]
        loss = self.loss_func(q_eval, q_target)
        self.optimizer.zero_grad()
        loss.backward()
        self.optimizer.step()


dqn = DQN()
print('\nCollecting experience...')
for i_episode in range(4000):
    s = env.reset()
    while True:
        env.render()

        a = dqn.choose_action(s)
        # take action
        s_, r, done, info = env.step(a)

        # modify the reward
        x, x_dot, theta, theta_dot = s_
        r1 = (env.x_threshold - abs(x)) / env.x_threshold - 0.8
        r2 = (env.theta_threshold_radians - abs(theta)) / env.theta_threshold_radians - 0.5
        r = r1 + r2

        dqn.store_transaction(s, a, r, s_)

        if dqn.memory_counter > MEMORY_CAPACITY:
            dqn.learn()

        if done:
            break
        s = s_

实验效果：