強化學習 DQN 實戰GYM下的CartPole遊戲

代碼和解釋

安裝依賴

!pip uninstall -y parl  # 說明：AIStudio預裝的parl版本太老，容易跟其他庫產生兼容性衝突，建議先卸載
!pip uninstall -y pandas scikit-learn # 提示：在AIStudio中卸載這兩個庫再import parl可避免warning提示，不卸載也不影響parl的使用

!pip install gym
!pip install paddlepaddle==1.6.3
!pip install parl==1.3.1

# 說明：安裝日誌中出現兩條紅色的關於 paddlehub 和 visualdl 的 ERROR 與parl無關，可以忽略，不影響使用

導入依賴

import parl
from parl import layers
import paddle.fluid as fluid
import copy
import numpy as np
import os
import gym
from parl.utils import logger

設置超參數

LEARN_FREQ = 5 # 訓練頻率，不需要每一個step都learn，攢一些新增經驗後再learn，提高效率
MEMORY_SIZE = 20000    # replay memory的大小，越大越佔用內存
MEMORY_WARMUP_SIZE = 200  # replay_memory 裏需要預存一些經驗數據，再開啓訓練
BATCH_SIZE = 32   # 每次給agent learn的數據數量，從replay memory隨機裏sample一批數據出來
LEARNING_RATE = 0.001 # 學習率
GAMMA = 0.99 # reward 的衰減因子，一般取 0.9 到 0.999 不等

搭建Model、Algorithm、Agent架構

Model

class Model(parl.Model):
    def __init__(self, act_dim):
        hid1_size = 128
        hid2_size = 128
        # 3層全連接網絡
        self.fc1 = layers.fc(size=hid1_size, act='relu')
        self.fc2 = layers.fc(size=hid2_size, act='relu')
        self.fc3 = layers.fc(size=act_dim, act=None)

    def value(self, obs):
        # 定義網絡
        # 輸入state，輸出所有action對應的Q，[Q(s,a1), Q(s,a2), Q(s,a3)...]
        h1 = self.fc1(obs)
        h2 = self.fc2(h1)
        Q = self.fc3(h2)
        return Q

Algorithm

# from parl.algorithms import DQN # 也可以直接從parl庫中導入DQN算法

class DQN(parl.Algorithm):
    def __init__(self, model, act_dim=None, gamma=None, lr=None):
        """ DQN algorithm
        
        Args:
            model (parl.Model): 定義Q函數的前向網絡結構
            act_dim (int): action空間的維度，即有幾個action
            gamma (float): reward的衰減因子
            lr (float): learning rate 學習率.
        """
        self.model = model
        self.target_model = copy.deepcopy(model)

        assert isinstance(act_dim, int)
        assert isinstance(gamma, float)
        assert isinstance(lr, float)
        self.act_dim = act_dim
        self.gamma = gamma
        self.lr = lr

    def predict(self, obs):
        """ 使用self.model的value網絡來獲取 [Q(s,a1),Q(s,a2),...]
        """
        return self.model.value(obs)

    def learn(self, obs, action, reward, next_obs, terminal):
        """ 使用DQN算法更新self.model的value網絡
        """
        # 從target_model中獲取 max Q' 的值，用於計算target_Q
        next_pred_value = self.target_model.value(next_obs)
        best_v = layers.reduce_max(next_pred_value, dim=1)
        best_v.stop_gradient = True  # 阻止梯度傳遞
        terminal = layers.cast(terminal, dtype='float32')
        target = reward + (1.0 - terminal) * self.gamma * best_v

        pred_value = self.model.value(obs)  # 獲取Q預測值
        # 將action轉onehot向量，比如：3 => [0,0,0,1,0]
        action_onehot = layers.one_hot(action, self.act_dim)
        action_onehot = layers.cast(action_onehot, dtype='float32')
        # 下面一行是逐元素相乘，拿到action對應的 Q(s,a)
        # 比如：pred_value = [[2.3, 5.7, 1.2, 3.9, 1.4]], action_onehot = [[0,0,0,1,0]]
        #  ==> pred_action_value = [[3.9]]
        pred_action_value = layers.reduce_sum(
            layers.elementwise_mul(action_onehot, pred_value), dim=1)

        # 計算 Q(s,a) 與 target_Q的均方差，得到loss
        cost = layers.square_error_cost(pred_action_value, target)
        cost = layers.reduce_mean(cost)
        optimizer = fluid.optimizer.Adam(learning_rate=self.lr)  # 使用Adam優化器
        optimizer.minimize(cost)
        return cost

    def sync_target(self):
        """ 把 self.model 的模型參數值同步到 self.target_model
        """
        self.model.sync_weights_to(self.target_model)

Agent

class Agent(parl.Agent):
    def __init__(self,
                 algorithm,
                 obs_dim,
                 act_dim,
                 e_greed=0.1,
                 e_greed_decrement=0):
        assert isinstance(obs_dim, int)
        assert isinstance(act_dim, int)
        self.obs_dim = obs_dim
        self.act_dim = act_dim
        super(Agent, self).__init__(algorithm)

        self.global_step = 0
        self.update_target_steps = 200  # 每隔200個training steps再把model的參數複製到target_model中

        self.e_greed = e_greed  # 有一定概率隨機選取動作，探索
        self.e_greed_decrement = e_greed_decrement  # 隨着訓練逐步收斂，探索的程度慢慢降低

    def build_program(self):
        self.pred_program = fluid.Program()
        self.learn_program = fluid.Program()

        with fluid.program_guard(self.pred_program):  # 搭建計算圖用於 預測動作，定義輸入輸出變量
            obs = layers.data(
                name='obs', shape=[self.obs_dim], dtype='float32')
            self.value = self.alg.predict(obs)

        with fluid.program_guard(self.learn_program):  # 搭建計算圖用於 更新Q網絡，定義輸入輸出變量
            obs = layers.data(
                name='obs', shape=[self.obs_dim], dtype='float32')
            action = layers.data(name='act', shape=[1], dtype='int32')
            reward = layers.data(name='reward', shape=[], dtype='float32')
            next_obs = layers.data(
                name='next_obs', shape=[self.obs_dim], dtype='float32')
            terminal = layers.data(name='terminal', shape=[], dtype='bool')
            self.cost = self.alg.learn(obs, action, reward, next_obs, terminal)

    def sample(self, obs):
        sample = np.random.rand()  # 產生0~1之間的小數
        if sample < self.e_greed:
            act = np.random.randint(self.act_dim)  # 探索：每個動作都有概率被選擇
        else:
            act = self.predict(obs)  # 選擇最優動作
        self.e_greed = max(
            0.01, self.e_greed - self.e_greed_decrement)  # 隨着訓練逐步收斂，探索的程度慢慢降低
        return act

    def predict(self, obs):  # 選擇最優動作
        obs = np.expand_dims(obs, axis=0)
        pred_Q = self.fluid_executor.run(
            self.pred_program,
            feed={'obs': obs.astype('float32')},
            fetch_list=[self.value])[0]
        pred_Q = np.squeeze(pred_Q, axis=0)
        act = np.argmax(pred_Q)  # 選擇Q最大的下標，即對應的動作
        return act

    def learn(self, obs, act, reward, next_obs, terminal):
        # 每隔200個training steps同步一次model和target_model的參數
        if self.global_step % self.update_target_steps == 0:
            self.alg.sync_target()
        self.global_step += 1

        act = np.expand_dims(act, -1)
        feed = {
            'obs': obs.astype('float32'),
            'act': act.astype('int32'),
            'reward': reward,
            'next_obs': next_obs.astype('float32'),
            'terminal': terminal
        }
        cost = self.fluid_executor.run(
            self.learn_program, feed=feed, fetch_list=[self.cost])[0]  # 訓練一次網絡
        return cost

ReplayMemory

import random
import collections
import numpy as np


class ReplayMemory(object):
    def __init__(self, max_size):
        self.buffer = collections.deque(maxlen=max_size)

    # 增加一條經驗到經驗池中
    def append(self, exp):
        self.buffer.append(exp)

    # 從經驗池中選取N條經驗出來
    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:
            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)

Training && Test

# 訓練一個episode
def run_episode(env, agent, rpm):
    total_reward = 0
    obs = env.reset()
    step = 0
    while True:
        step += 1
        action = agent.sample(obs)  # 採樣動作，所有動作都有概率被嘗試到
        next_obs, reward, done, _ = env.step(action)
        rpm.append((obs, action, reward, next_obs, done))

        # train model
        if (len(rpm) > MEMORY_WARMUP_SIZE) and (step % LEARN_FREQ == 0):
            (batch_obs, batch_action, batch_reward, batch_next_obs,
             batch_done) = rpm.sample(BATCH_SIZE)
            train_loss = agent.learn(batch_obs, batch_action, batch_reward,
                                     batch_next_obs,
                                     batch_done)  # s,a,r,s',done

        total_reward += reward
        obs = next_obs
        if done:
            break
    return total_reward


# 評估 agent, 跑 5 個episode，總reward求平均
def evaluate(env, agent, render=False):
    eval_reward = []
    for i in range(5):
        obs = env.reset()
        episode_reward = 0
        while True:
            action = agent.predict(obs)  # 預測動作，只選最優動作
            obs, reward, done, _ = env.step(action)
            episode_reward += reward
            if render:
                env.render()
            if done:
                break
        eval_reward.append(episode_reward)
    return np.mean(eval_reward)

創建環境和Agent，創建經驗池，啓動訓練，保存模型

env = gym.make('CartPole-v0')  # CartPole-v0: 預期最後一次評估總分 > 180（最大值是200）
action_dim = env.action_space.n  # CartPole-v0: 2
obs_shape = env.observation_space.shape  # CartPole-v0: (4,)

rpm = ReplayMemory(MEMORY_SIZE)  # DQN的經驗回放池

# 根據parl框架構建agent
model = Model(act_dim=action_dim)
algorithm = DQN(model, act_dim=action_dim, gamma=GAMMA, lr=LEARNING_RATE)
agent = Agent(
    algorithm,
    obs_dim=obs_shape[0],
    act_dim=action_dim,
    e_greed=0.1,  # 有一定概率隨機選取動作，探索
    e_greed_decrement=1e-6)  # 隨着訓練逐步收斂，探索的程度慢慢降低

# 加載模型
# save_path = './dqn_model.ckpt'
# agent.restore(save_path)

# 先往經驗池裏存一些數據，避免最開始訓練的時候樣本豐富度不夠
while len(rpm) < MEMORY_WARMUP_SIZE:
    run_episode(env, agent, rpm)

max_episode = 2000

# 開始訓練
episode = 0
while episode < max_episode:  # 訓練max_episode個回合，test部分不計算入episode數量
    # train part
    for i in range(0, 50):
        total_reward = run_episode(env, agent, rpm)
        episode += 1

    # test part
    eval_reward = evaluate(env, agent, render=False)  # render=True 查看顯示效果
    logger.info('episode:{}    e_greed:{}   test_reward:{}'.format(
        episode, agent.e_greed, eval_reward))

# 訓練結束，保存模型
save_path = './dqn_model.ckpt'
agent.save(save_path)

運行結果