Question

所以我现在正在观看与 Markov Chain 相关的代码，问题是我不知道这段代码是如何工作的。

transition_probabilities = [
        [[0.7, 0.3, 0.0], [1.0, 0.0, 0.0], [0.8, 0.2, 0.0]], # in s0, if action a0 then proba 0.7 to state s0 and 0.3 to state s1, etc.
        [[0.0, 1.0, 0.0], None, [0.0, 0.0, 1.0]],
        [None, [0.8, 0.1, 0.1], None],
    ]

rewards = [
        [[+10, 0, 0], [0, 0, 0], [0, 0, 0]],
        [[0, 0, 0], [0, 0, 0], [0, 0, -50]],
        [[0, 0, 0], [+40, 0, 0], [0, 0, 0]],
    ]

possible_actions = [[0, 1, 2], [0, 2], [1]]

def policy_fire(state):
    return [0, 2, 1][state]

def policy_random(state):
    return rnd.choice(possible_actions[state])

def policy_safe(state):
    return [0, 0, 1][state]

class MDPEnvironment(object):
    def __init__(self, start_state=0):
        self.start_state=start_state
        self.reset()
    def reset(self):
        self.total_rewards = 0
        self.state = self.start_state
    def step(self, action):
        next_state = rnd.choice(range(3), p=transition_probabilities[self.state][action])
        reward = rewards[self.state][action][next_state]
        self.state = next_state
        self.total_rewards += reward
        return self.state, reward

def run_episode(policy, n_steps, start_state=0, display=True):
    env = MDPEnvironment()
    if display:
        print("States (+rewards):", end=" ")
    for step in range(n_steps):
        if display:
            if step == 10:
                print("...", end=" ")
            elif step < 10:
                print(env.state, end=" ")
        action = policy(env.state)
        state, reward = env.step(action)
        if display and step < 10:
            if reward:
                print("({})".format(reward), end=" ")
    if display:
        print("Total rewards =", env.total_rewards)
    return env.total_rewards

for policy in (policy_fire, policy_random, policy_safe):
    all_totals = []
    print(policy.__name__)
    for episode in range(1000):
        all_totals.append(run_episode(policy, n_steps=100, display=(episode<5)))
    print("Summary: mean={:.1f}, std={:1f}, min={}, max={}".format(np.mean(all_totals), np.std(all_totals), np.min(all_totals), np.max(all_totals)))
    print()

在第16行中，有一个函数只返回索引。我从来没有听说过这样的事情。我所知道的索引是它必须有一个相应的 l_value ，以便索引可以订阅数组内的元素或任何东西。那么你们能告诉我发生了什么事吗？

Answer 1

第15-16行：

def policy_fire(state):
    return [0, 2, 1][state]

此函数假定state是0和2之间的整数，并使用该值索引列表[0, 2, 1]并返回结果值。所以例如policy_fire(1)将返回2。

此函数在函数run_episode中调用，env.state作为参数，其中env = MDPEnvironment()。

Python函数只返回索引

1 个答案: