if __name__ == "__main__":
env = Maze()
RL = DuelingDQN(
env.n_actions,
env.n_features, #observation/state 的属性，如长宽高
learning_rate=0.01,
reward_decay=0.9,
e_greedy=0.9,
dueling=True,
replace_target_iter=200, # 每 200 步替换一次 target_net 的参数
memory_size=2000, # 记忆上限
# output_graph=True # 是否输出 tensorboard 文件
)
env.after(100, run_maze) #进行强化学习训练
env.mainloop()
# 观看训练时间曲线
his_dueling = np.vstack((episodes, steps))
file = open('his_dueling', 'wb')
pickle.dump(his_dueling, file)
file.close()
plt.plot(his_dueling[0, :],
his_dueling[1, :] - his_dueling[1, 0],
c='b',
label='Dueling DQN')
plt.legend(loc='best') # legend图例，其中’loc’参数有多种，’best’表示自动分配最佳位置
plt.ylabel('total training time')
plt.xlabel('episode')
plt.grid() # 显示网格线 1=True=默认显示；0=False=不显示
env.render()
# RL take action and get next observation and reward
observation_, reward, done = env.step(action)
# RL choose action based on next observation
action_ = RL.choose_action(str(observation_))
# RL learn from this transition (s, a, r, s, a) ==> Sarsa
RL.learn(str(observation), action, reward, str(observation_),
action_)
# swap observation and action
observation = observation_
action = action_
# break while loop when end of this episode
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()