Java调用Python强化学习的例子

Java调用Python强化学习的例子

1. 在java类中直接执行python语句

此方法需要引用 org.python包，需要下载Jpython。在这里先介绍一下Jpython。下面引入百科的解释：
Jython是一种完整的语言，而不是一个Java翻译器或仅仅是一个Python编译器，它是一个Python语言在Java中的完全实现。Jython也有很多从CPython中继承的模块库。最有趣的事情是Jython不像CPython或其他任何高级语言，它提供了对其实现语言的一切存取。所以Jython不仅给你提供了Python的库，同时也提供了所有的Java类。这使其有一个巨大的资源库。
这里我建议下载最新版本的Jpython，因为可以使用的python函数库会比老版本的多些，目前最新版本为2.7.1。
下载jar包请点击Download Jython 2.7.1 - Standalone Jar
下载安装程序请点击Download Jython 2.7.1 - Installer
如果使用maven依赖添加的话，使用下面的语句

<!-- https://mvnrepository.com/artifact/org.python/jython-standalone -->
<dependency>
    <groupId>org.python</groupId>
    <artifactId>jython-standalone</artifactId>
    <version>2.7.1</version>
</dependency>

以上准备好了，就可以直接在java类中写python语句了，具体代码如下：

PythonInterpreter interpreter = new PythonInterpreter();
interpreter.exec("a=[5,2,3,9,4,0]; ");
interpreter.exec("print(sorted(a));");  //此处python语句是3.x版本的语法
interpreter.exec("print sorted(a);");   //此处是python语句是2.x版本的语法

## 2. 在java中调用本地python脚本
首先在本地建立一个python脚本，命名为add.py，写了一个简单的两个数做加法的函数，代码如下：

def add(a,b):
  return a + b

python的功能函数已经写好，接下来我们写一个java的测试类（同样需要用到Jpython包），来测试一下是否可以运行成功。代码如下：

import org.python.core.PyFunction;
import org.python.core.PyInteger;
import org.python.core.PyObject;
import org.python.util.PythonInterpreter;
 
public class Java_Python_test {
 
    public static void main(String[] args) {
        // TODO Auto-generated method stub
        PythonInterpreter interpreter = new PythonInterpreter();
        interpreter.execfile("D:\\add.py");
 
        // 第一个参数为期望获得的函数（变量）的名字，第二个参数为期望返回的对象类型
        PyFunction pyFunction = interpreter.get("add", PyFunction.class);
        int a = 5, b = 10;
        //调用函数，如果函数需要参数，在Java中必须先将参数转化为对应的“Python类型”
        PyObject pyobj = pyFunction.__call__(new PyInteger(a), new PyInteger(b)); 
        System.out.println("the anwser is: " + pyobj);
    }
}

注意：以上两个方法虽然都可以调用python程序，但是使用Jpython调用的python库不是很多，如果你用以上两个方法调用，而python的程序中使用到第三方库，这时就会报错java ImportError: No module named xxx。遇到这种情况推荐使用下面的方法，即可解决该问题。

3. 使用Runtime.getRuntime()执行脚本文件（推荐）
本人觉得这种方法是最好的，并不需要引入相关的jar包，直接使用JDK自带的Runtime
下面我们来调一下强化学习的一个例子（相关的numpy和pandas第三方库自行去下载）：
1.python强化学习代码
maze_env.py

import numpy as np
import time
import sys
if sys.version_info.major == 2:
    import Tkinter as tk
else:
    import tkinter as tk


UNIT = 40   # pixels
MAZE_H = 4  # grid height
MAZE_W = 4  # grid width


class Maze(tk.Tk, object):
    def __init__(self):
        super(Maze, self).__init__()
        self.action_space = ['u', 'd', 'l', 'r']
        self.n_actions = len(self.action_space)
        self.title('maze')
        self.geometry('{0}x{1}'.format(MAZE_H * UNIT, MAZE_H * UNIT))
        self._build_maze()

    def _build_maze(self):
        self.canvas = tk.Canvas(self, bg='white',
                           height=MAZE_H * UNIT,
                           width=MAZE_W * UNIT)

        # create grids
        for c in range(0, MAZE_W * UNIT, UNIT):
            x0, y0, x1, y1 = c, 0, c, MAZE_H * UNIT
            self.canvas.create_line(x0, y0, x1, y1)
        for r in range(0, MAZE_H * UNIT, UNIT):
            x0, y0, x1, y1 = 0, r, MAZE_W * UNIT, r
            self.canvas.create_line(x0, y0, x1, y1)

        # create origin
        origin = np.array([20, 20])

        # hell
        hell1_center = origin + np.array([UNIT * 2, UNIT])
        self.hell1 = self.canvas.create_rectangle(
            hell1_center[0] - 15, hell1_center[1] - 15,
            hell1_center[0] + 15, hell1_center[1] + 15,
            fill='black')
        # hell
        hell2_center = origin + np.array([UNIT, UNIT * 2])
        self.hell2 = self.canvas.create_rectangle(
            hell2_center[0] - 15, hell2_center[1] - 15,
            hell2_center[0] + 15, hell2_center[1] + 15,
            fill='black')

        # create oval
        oval_center = origin + UNIT * 2
        self.oval = self.canvas.create_oval(
            oval_center[0] - 15, oval_center[1] - 15,
            oval_center[0] + 15, oval_center[1] + 15,
            fill='yellow')

        # create red rect
        self.rect = self.canvas.create_rectangle(
            origin[0] - 15, origin[1] - 15,
            origin[0] + 15, origin[1] + 15,
            fill='red')

        # pack all
        self.canvas.pack()

    def reset(self):
        self.update()
        time.sleep(0.5)
        self.canvas.delete(self.rect)
        origin = np.array([20, 20])
        self.rect = self.canvas.create_rectangle(
            origin[0] - 15, origin[1] - 15,
            origin[0] + 15, origin[1] + 15,
            fill='red')
        # return observation
        return self.canvas.coords(self.rect)

    def step(self, action):
        s = self.canvas.coords(self.rect)
        base_action = np.array([0, 0])
        if action == 0:   # up
            if s[1] > UNIT:
                base_action[1] -= UNIT
        elif action == 1:   # down
            if s[1] < (MAZE_H - 1) * UNIT:
                base_action[1] += UNIT
        elif action == 2:   # right
            if s[0] < (MAZE_W - 1) * UNIT:
                base_action[0] += UNIT
        elif action == 3:   # left
            if s[0] > UNIT:
                base_action[0] -= UNIT

        self.canvas.move(self.rect, base_action[0], base_action[1])  # move agent

        s_ = self.canvas.coords(self.rect)  # next state

        # reward function
        if s_ == self.canvas.coords(self.oval):
            reward = 1
            done = True
            s_ = 'terminal'
        elif s_ in [self.canvas.coords(self.hell1), self.canvas.coords(self.hell2)]:
            reward = -1
            done = True
            s_ = 'terminal'
        else:
            reward = 0
            done = False

        return s_, reward, done

    def render(self):
        time.sleep(0.1)
        self.update()

RL_brain.py

import numpy as np
import pandas as pd


class RL(object):
    def __init__(self, action_space, learning_rate=0.01, reward_decay=0.9, e_greedy=0.9):
        self.actions = action_space  # a list
        self.lr = learning_rate
        self.gamma = reward_decay
        self.epsilon = e_greedy

        self.q_table = pd.DataFrame(columns=self.actions, dtype=np.float64)

    def check_state_exist(self, state):
        if state not in self.q_table.index:
            # append new state to q table
            self.q_table = self.q_table.append(
                pd.Series(
                    [0]*len(self.actions),
                    index=self.q_table.columns,
                    name=state,
                )
            )

    def choose_action(self, observation):
        self.check_state_exist(observation)
        # action selection
        if np.random.rand() < self.epsilon:
            # choose best action
            state_action = self.q_table.loc[observation, :]
            # some actions may have the same value, randomly choose on in these actions
            action = np.random.choice(state_action[state_action == np.max(state_action)].index)
        else:
            # choose random action
            action = np.random.choice(self.actions)
        return action

    def learn(self, *args):
        pass


# off-policy
class QLearningTable(RL):
    def __init__(self, actions, learning_rate=0.01, reward_decay=0.9, e_greedy=0.9):
        super(QLearningTable, self).__init__(actions, learning_rate, reward_decay, e_greedy)

    def learn(self, s, a, r, s_):
        self.check_state_exist(s_)
        q_predict = self.q_table.loc[s, a]
        if s_ != 'terminal':
            q_target = r + self.gamma * self.q_table.loc[s_, :].max()  # next state is not terminal
        else:
            q_target = r  # next state is terminal
        self.q_table.loc[s, a] += self.lr * (q_target - q_predict)  # update


# on-policy
class SarsaTable(RL):

    def __init__(self, actions, learning_rate=0.01, reward_decay=0.9, e_greedy=0.9):
        super(SarsaTable, self).__init__(actions, learning_rate, reward_decay, e_greedy)

    def learn(self, s, a, r, s_, a_):
        self.check_state_exist(s_)
        q_predict = self.q_table.loc[s, a]
        if s_ != 'terminal':
            q_target = r + self.gamma * self.q_table.loc[s_, a_]  # q_target基于选好的a_而不是Q(s_)的最大值
        else:
            q_target = r
        self.q_table.loc[s, a] += self.lr * (q_target - q_predict)  # 更新q_table

run_this.py

from maze_env import Maze
from RL_brain import SarsaTable


def update():
    for episode in range(100):
        # 初始化环境
        observation = env.reset()

        # Sarsa根据state观测选择行为
        action = RL.choose_action(str(observation))

        while True:
            # 刷新环境
            env.render()

            # 在环境中采取行为，获得下一个state_(observation_),reward，和终止信号
            observation_, reward, done = env.step(action)

            # 根据下一个state(observation_)选取下一个action_
            action_ = RL.choose_action(str(observation_))

            #从(s, a, r, s, a)中学习，更新Q_table的参数
            RL.learn(str(observation), action, reward, str(observation_), action_)

            # 将下一个的observation_和action_当成对应下一步的参数
            observation = observation_
            action = action_


            if done:
                break

    # end of game
    print('game over')
    env.destroy()

if __name__ == "__main__":
    env = Maze()
    RL = SarsaTable(actions=list(range(env.n_actions)))
    env.after(100, update)
    env.mainloop()

下面是Runtime.getRuntime()调用python的Java代码：

    @Test
    public void test() throws IOException {
        Process process = Runtime.getRuntime().exec("python d:\\Sarsa\\run_this.py");
    }

运行结果如下：

到此关于Java调python的方法就总结完毕了，本人强烈推荐第三种方法。