两个作业的对比:
- Lesson2 表格型方法—— Q-learning
(小心探索)
# 根据输入观察值,采样输出的动作值,带探索
def sample(self, obs):
if np.random.uniform(0, 1) < (1.0 - self.epsilon): #根据table的Q值选动作
action = self.predict(obs)
else:
action = np.random.choice(self.act_n) #有一定概率随机探索选取一个动作
return action
# 根据输入观察值,预测输出的动作值
def predict(self, obs):
Q_list = self.Q[obs, :]
maxQ = np.max(Q_list)
action_list = np.where(Q_list == maxQ)[0] # maxQ可能对应多个action
action = np.random.choice(action_list)
return action
# 学习方法,也就是更新Q-table的方法
def learn(self, obs, action, reward, next_obs, done):
""" off-policy
obs: 交互前的obs, s_t
action: 本次交互选择的action, a_t
reward: 本次动作获得的奖励r
next_obs: 本次交互后的obs, s_t+1
done: episode是否结束
"""
predict_Q = self.Q[obs, action]
if done:
target_Q = reward # 没有下一个状态了
else:
target_Q = reward + self.gamma * np.max(self.Q[next_obs, :]) # Q-learning
self.Q[obs, action] += self.lr * (target_Q - predict_Q) # 修正q
- Lesson2 表格型方法——Sarsa
(疯狂探索)
# 根据输入观察值,采样输出的动作值,带探索
def sample(self, obs):
if np.random.uniform(0, 1) < (1.0 - self.epsilon): #根据table的Q值选动作
action = self.predict(obs)
else:
action = np.random.choice(self.act_n) #有一定概率随机探索选取一个动作
return action
# 根据输入观察值,预测输出的动作值
def predict(self, obs):
Q_list = self.Q[obs, :]
maxQ = np.max(Q_list)
action_list = np.where(Q_list == maxQ)[0] # maxQ可能对应多个action
action = np.random.choice(action_list)
return action
# 学习方法,也就是更新Q-table的方法
def learn(self, obs, action, reward, next_obs, next_action, done):
""" on-policy
obs: 交互前的obs, s_t
action: 本次交互选择的action, a_t
reward: 本次动作获得的奖励r
next_obs: 本次交互后的obs, s_t+1
next_action: 根据当前Q表格, 针对next_obs会选择的动作, a_t+1
done: episode是否结束
"""
predict_Q = self.Q[obs, action]
if done:
target_Q = reward # 没有下一个状态了
else:
target_Q = reward + self.gamma * self.Q[next_obs, next_action] # Sarsa
self.Q[obs, action] += self.lr * (target_Q - predict_Q) # 修正q