採用兩個深度神經網絡（DNN）來學習狀態到動作的映射，和神經網絡權重的更新，以解決Q表狀態-動作值決策時空間增長而計算存儲高複雜度的問題。此外，還包括double DQN（解決過擬合），Prioritized Experience Replay（解決以更低的計算時間獲得收斂效果），和Dueling DQN這些對DQN的提升方法。
"""
Zoe大腦RL_brain
"""
import os
os.environ["TF_CPP_MIN_LOG_LEVEL"] = '2'
import numpy as np
import pandas as pd
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
np.random.seed(1)
tf.set_random_seed(1)
# Deep Q Network off-policy
class DeepQNetwork:
def __init__(
self,
n_actions,
n_features,
learning_rate=0.01,
reward_decay=0.9,
e_greedy=0.9,
replace_target_iter=300,
memory_size=500,
batch_size=32,
e_greedy_increment=None,
output_graph=False,
):
self.n_actions = n_actions
self.n_features = n_features
self.lr = learning_rate
self.gamma = reward_decay
self.epsilon_max = e_greedy
self.replace_target_iter = replace_target_iter
self.memory_size = memory_size
self.batch_size = batch_size
self.epsilon_increment = e_greedy_increment
self.epsilon = 0 if e_greedy_increment is not None else self.epsilon_max
# total learning step
self.learn_step_counter = 0
# initialize zero memory [s, a, r, s_]
self.memory = np.zeros((self.memory_size, n_features * 2 + 2))
# consist of [target_net, evaluate_net]
self._build_net()
t_params = tf.get_collection('target_net_params')
e_params = tf.get_collection('eval_net_params')
self.replace_target_op = [tf.assign(t, e) for t, e in zip(t_params, e_params)]
self.sess = tf.Session()
if output_graph:
# $ tensorboard --logdir=logs
# tf.train.SummaryWriter soon be deprecated, use following
tf.summary.FileWriter("logs/", self.sess.graph)
self.sess.run(tf.global_variables_initializer())
self.cost_his = []
# [n.name for n in tf.get_default_graph().as_graph_def().node]
# print([n.name for n in tf.get_default_graph().as_graph_def().node])
tensor_name_list = [tensor.name for tensor in tf.get_default_graph().as_graph_def().node]
txt_path = './txt/節點名稱'
full_path = txt_path+ '.txt'
for tensor_name in tensor_name_list:
name = tensor_name + '\n'
file = open(full_path,'a+')
file.write(name)
file.close()
def _build_net(self):
#--------------------build evaluate_net-----------------
self.s = tf.placeholder(tf.float32, [None, self.n_features], name='s')
self.q_target = tf.placeholder(tf.float32, [None, self.n_actions], name='Q_target')
with tf.variable_scope('eval_net'):
# c_names(collections_names) are the collections to store variables
c_names, n_l1, w_initializer, b_initializer = \
['eval_net_params', tf.GraphKeys.GLOBAL_VARIABLES], 10, \
tf.random_normal_initializer(0., 0.3), tf.constant_initializer(0.1) # config of layers
# first layer. collections is used later when assign to target net
with tf.variable_scope('l1'):
w1 = tf.get_variable('w1', [self.n_features, n_l1], initializer=w_initializer,collections=c_names)
b1 = tf.get_variable('b1', [1, n_l1], initializer=b_initializer, collections=c_names)
l1 = tf.nn.relu(tf.matmul(self.s, w1) + b1)
# second layer. collections is used later when assign to target net
with tf.variable_scope('l2'):
w2 = tf.get_variable('w2', [n_l1, self.n_actions], initializer=w_initializer, collections=c_names)
b2 = tf.get_variable('b2', [1, self.n_actions], initializer=b_initializer, collections=c_names)
self.q_eval = tf.matmul(l1, w2) + b2
with tf.variable_scope('loss'):
self.loss = tf.reduce_mean(tf.squared_difference(self.q_target, self.q_eval))
with tf.variable_scope('train'):
self._train_op = tf.train.RMSPropOptimizer(self.lr).minimize(self.loss)
#-----------------------------build target_net-------------------------------
self.s_ = tf.placeholder(tf.float32, [None, self.n_features], name='s_')
with tf.variable_scope('target_net'):
# c_names(collections_names) are the collections to store variables
c_names = ['target_net_params', tf.GraphKeys.GLOBAL_VARIABLES]
# first layer. collections is used later when assign to target net
with tf.variable_scope('l1'):
w1 = tf.get_variable('w1', [self.n_features, n_l1], initializer=w_initializer, collections=c_names)
b1 = tf.get_variable('b1', [1, n_l1], initializer=b_initializer, collections=c_names)
l1 = tf.nn.relu(tf.matmul(self.s_, w1) + b1)
# second layer. collections is used later when assign to target net
with tf.variable_scope('l2'):
w2 = tf.get_variable('w2', [n_l1, self.n_actions], initializer=w_initializer, collections=c_names)
b2 = tf.get_variable('b2', [1, self.n_actions], initializer=b_initializer, collections=c_names)
self.q_next = tf.matmul(l1, w2) + b2
def store_transition(self, s, a, r, s_):
if not hasattr(self, 'memory_counter'):
self.memory_counter = 0
transition = np.hstack((s, [a, r], s_))
# replace the old memory with new memory
index = self.memory_counter % self.memory_size
self.memory[index, :] = transition
self.memory_counter += 1
def choose_action(self, observation):
# to have batch dimension when feed into tf placeholder
observation = observation[np.newaxis, :]
if np.random.uniform() < self.epsilon:
# forward feed the observation and get q value for every actions
actions_value = self.sess.run(self.q_eval, feed_dict={self.s:observation})
action = np.argmax(actions_value)
else:
action = np.random.randint(0, self.n_actions)
return action
def learn(self):
# check to replace target parameters
if self.learn_step_counter % self.replace_target_iter == 0:
self.sess.run(self.replace_target_op)
print('\ntarget_params_replaced\n')
# sample batch memory from all memory
if self.memory_counter > self.memory_size:
sample_index = np.random.choice(self.memory_size, size=self.batch_size)
else:
sample_index = np.random.choice(self.memory_counter, size=self.batch_size)
batch_memory = self.memory[sample_index, :]
q_next, q_eval = self.sess.run(
[self.q_next, self.q_eval],
feed_dict={
self.s_:batch_memory[:, -self.n_features:],
self.s:batch_memory[:, :self.n_features],
})
# change q_target w.r.t q_eval's action
q_target = q_eval.copy()
batch_index = np.arange(self.batch_size, dtype=np.int32)
eval_act_index = batch_memory[:, self.n_features].astype(int)
reward = batch_memory[:, self.n_features + 1]
q_target[batch_index, eval_act_index] = reward + self.gamma * np.max(q_next,axis=1)
# print('輸出')
# print(q_target[batch_index, eval_act_index])
# print(q_target)
# print(q_next)
# print(np.max(q_next))
"""
For example in this batch I have 2 samples and 3 actions:
q_eval =
[[1, 2, 3],
[4, 5, 6]]
q_target = q_eval =
[[1, 2, 3],
[4, 5, 6]]
Then change q_target with the real q_target value w.r.t the q_eval's action.
For example in:
sample 0, I took action 0, and the max q_target value is -1;
sample 1, I took action 2, and the max q_target value is -2;
q_target =
[[-1, 2, 3],
[4, 5, -2]]
So the (q_target-q_eval) becomes:
[[(-1-1), 0, 0],
[0, 0, (-2)-(6)]]
We then backpropagate this error w.r.t the corresponding action to network,
leave other action as error=0 cause we didn't choose it.
"""
# train eval network
_, self.cost = self.sess.run([self._train_op, self.loss],
feed_dict={self.s:batch_memory[:, :self.n_features],
self.q_target:q_target})
self.cost_his.append(self.cost)
# increasing epsilon
self.epsilon = self.epsilon + self.epsilon_increment if self.epsilon < self.epsilon_max else self.epsilon_max
self.learn_step_counter += 1
def plot_cost(self):
import matplotlib.pyplot as plt
plt.plot(np.arange(len(self.cost_his)), self.cost_his)
plt.ylabel('Cost')
plt.xlabel('traning steps')
plt.show()
"""
if __name__ == "__main__":
DQN = DeepQNetwork(4,2, output_graph=True)
"""
"""
爬山小車案例
"""
import gym
from RL_brain import DeepQNetwork
env = gym.make('MountainCar-v0')
env = env.unwrapped
print(env.action_space)
print(env.observation_space)
print(env.observation_space.high)
print(env.observation_space.low)
RL = DeepQNetwork(n_actions=3, n_features=2, learning_rate=0.001, e_greedy=0.9,
replace_target_iter=300, memory_size=3000,
e_greedy_increment=0.0002,)
total_steps = 0
for i_episode in range(10):
observation = env.reset()
ep_r = 0
while True:
env.render()
action = RL.choose_action(observation)
observation_, reward, done, info = env.step(action)
position, velocity = observation_
# the higher the better
reward = abs(position - (-0.5)) # r in [0, 1]
RL.store_transition(observation, action, reward, observation_)
if total_steps > 1000:
RL.learn()
ep_r += reward
if done:
get = '| Get' if observation_[0] >= env.unwrapped.goal_position else '| ----'
print('Epi: ', i_episode,
get,
'| Ep_r: ', round(ep_r, 4),
'| Epsilon: ', round(RL.epsilon, 2))
break
observation = observation_
total_steps += 1
RL.plot_cost()
"""
小拖車車杆案例
"""
import gym
from RL_brain import DeepQNetwork
env = gym.make('CartPole-v0')
env = env.unwrapped
print(env.action_space)
print(env.observation_space)
print(env.observation_space.high)
print(env.observation_space.low)
RL = DeepQNetwork(n_actions=env.action_space.n,
n_features=env.observation_space.shape[0],
learning_rate=0.01, e_greedy=0.9,
replace_target_iter=100, memory_size=2000,
e_greedy_increment=0.001,)
total_steps = 0
for i_episode in range(100):
observation = env.reset()
ep_r = 0
while True:
env.render()
action = RL.choose_action(observation)
observation_, reward, done, info = env.step(action)
# the smaller theta and closer to center the better
x, x_dot, theta, theta_dot = observation_
r1 = (env.x_threshold - abs(x))/env.x_threshold - 0.8
r2 = (env.theta_threshold_radians - abs(theta))/env.theta_threshold_radians - 0.5
reward = r1 + r2
RL.store_transition(observation, action, reward, observation_)
ep_r += reward
if total_steps > 1000:
RL.learn()
if done:
print('episode: ', i_episode,
'ep_r: ', round(ep_r, 2),
'epsilon: ', round(RL.epsilon, 2))
break
observation = observation_
total_steps += 1
RL.plot_cost()