【发布时间】：2020-05-14 07:48:43
【问题描述】：
我实现了 Q-learning 算法，并在 OpenAI 健身房的 FrozenLake-v0 上使用了它。 我在 10000 集的训练期间获得了 185 个总奖励，在测试期间获得了 7333 个总奖励。 这样好吗？
我还尝试了 Dyna-Q 算法。但它的性能比 Q-learning 差。 大约。训练期间的总奖励为 200 个，测试期间的总奖励为 700-900 个，共 10000 集，包含 50 个计划步骤。
为什么会这样？
下面是代码。代码有问题吗？
# Setup
env = gym.make('FrozenLake-v0')
epsilon = 0.9
lr_rate = 0.1
gamma = 0.99
planning_steps = 0
total_episodes = 10000
max_steps = 100
训练和测试()：
while t < max_steps:
action = agent.choose_action(state)
state2, reward, done, info = agent.env.step(action)
# Removed in testing
agent.learn(state, state2, reward, action)
agent.model.add(state, action, state2, reward)
agent.planning(planning_steps)
# Till here
state = state2
def add(self, state, action, state2, reward):
self.transitions[state, action] = state2
self.rewards[state, action] = reward
def sample(self, env):
state, action = 0, 0
# Random visited state
if all(np.sum(self.transitions, axis=1)) <= 0:
state = np.random.randint(env.observation_space.n)
else:
state = np.random.choice(np.where(np.sum(self.transitions, axis=1) > 0)[0])
# Random action in that state
if all(self.transitions[state]) <= 0:
action = np.random.randint(env.action_space.n)
else:
action = np.random.choice(np.where(self.transitions[state] > 0)[0])
return state, action
def step(self, state, action):
state2 = self.transitions[state, action]
reward = self.rewards[state, action]
return state2, reward
def choose_action(self, state):
if np.random.uniform(0, 1) < epsilon:
return self.env.action_space.sample()
else:
return np.argmax(self.Q[state, :])
def learn(self, state, state2, reward, action):
# predict = Q[state, action]
# Q[state, action] = Q[state, action] + lr_rate * (target - predict)
target = reward + gamma * np.max(self.Q[state2, :])
self.Q[state, action] = (1 - lr_rate) * self.Q[state, action] + lr_rate * target
def planning(self, n_steps):
# if len(self.transitions)>planning_steps:
for i in range(n_steps):
state, action = self.model.sample(self.env)
state2, reward = self.model.step(state, action)
self.learn(state, state2, reward, action)
【问题讨论】：
-
你解决过这个问题吗？我自己的直觉是，也许模型过度拟合了训练环境，导致了一个只在训练中效果很好的策略。然后你的测试环境太不同了，策略失败了。我没有看到任何迹象表明您正在设置随机种子，也许在第一步中尝试在训练和测试中将其修复为相同的值。如果 Dyna-Q 代理在此处的测试表现不佳，则说明代理本身存在错误。
标签： python reinforcement-learning q-learning