问用VowpalWabbit优化CTR (点击率)：如何选择合适的参数？
EN

Stack Overflow用户

提问于 2021-06-30 09:47:27

回答 1查看 236关注 0票数 0

我试图通过VowpalWabbit优化某些文章或广告(动作)的点击率，给出一个设备类型(上下文)(在本文大众教程之后)。然而，我无法使它可靠地收敛到最优动作。

我创建了一个最小的工作示例(对不起长度)：

import random
import numpy as np
from matplotlib import pyplot as plt
from vowpalwabbit import pyvw

plt.ion()

action_space = ["article-1", "article-2", "article-3"]

def running_mean(x, N):
    cumsum = np.cumsum(np.insert(x, 0, 0))
    return (cumsum[N:] - cumsum[:-N]) / float(N)

def to_vw_example_format(context, cb_label=None):
    if cb_label is not None:
        chosen_action, cost, prob = cb_label
    example_string = ""
    example_string += "shared |User device={} \n".format(context)
    for action in action_space:
        if cb_label is not None and action == chosen_action:
            example_string += "1:{}:{} ".format(cost, prob)
        example_string += "|Action ad={} \n".format(action)
    # Strip the last newline
    return example_string[:-1]

# definition of problem to solve, playing out the article with highest ctr given a context
context_to_action_ctr = {
    "device-1": {"article-1": 0.05, "article-2": 0.06, "article-3": 0.04},
    "device-2": {"article-1": 0.08, "article-2": 0.07, "article-3": 0.05},
    "device-3": {"article-1": 0.01, "article-2": 0.04, "article-3": 0.09},
    "device-4": {"article-1": 0.04, "article-2": 0.04, "article-3": 0.045},
    "device-5": {"article-1": 0.09, "article-2": 0.01, "article-3": 0.07},
    "device-6": {"article-1": 0.03, "article-2": 0.09, "article-3": 0.04}
}

#vw = f"--cb_explore 3 -q UA -q UU --epsilon 0.1"
vw = f"--cb_explore_adf -q UA -q UU --bag 5 "
#vw = f"--cb_explore_adf -q UA --epsilon 0.2"

actor = pyvw.vw(vw)

random_rewards = []
actor_rewards = []
optimal_rewards = []

for step in range(200000):

    # pick a random context
    device = random.choice(list(context_to_action_ctr.keys()))

    # let vw generate probability distribution
    # action_probabilities = np.array(actor.predict(f"|x device:{device}"))
    action_probabilities = np.array(actor.predict(to_vw_example_format(device)))

    # sample action
    probabilities = action_probabilities / action_probabilities.sum()
    action_idx = np.random.choice(len(probabilities), 1, p=probabilities)[0]
    probability = action_probabilities[action_idx]

    # get reward/regret
    action_to_reward_regret = {
        action: (1, 0) if random.random() < context_to_action_ctr[device][action] else (0, 1) for action in action_space
    }

    actor_action = action_space[action_idx]
    random_action = random.choice(action_space)
    optimal_action = {
        "device-1": "article-2",
        "device-2": "article-1",
        "device-3": "article-3",
        "device-4": "article-3",
        "device-5": "article-1",
        "device-6": "article-2",
    }[device]

    # update statistics
    actor_rewards.append(action_to_reward_regret[actor_action][0])
    random_rewards.append(action_to_reward_regret[random_action][0])
    optimal_rewards.append(action_to_reward_regret[optimal_action][0])

    # learn online
    reward, regret = action_to_reward_regret[actor_action]
    cost = -1 if reward == 1 else 0
    # actor.learn(f"{action_idx+1}:{cost}:{probability} |x device:{device}")
    actor.learn(to_vw_example_format(device, (actor_action, cost, probability)))


    if step % 100 == 0 and step > 1000:
        plt.clf()
        axes = plt.gca()
        plt.title("Reward over time")
        plt.plot(running_mean(actor_rewards, 10000), label=str(vw))
        plt.plot(running_mean(random_rewards, 10000), label="Random actions")
        plt.plot(running_mean(optimal_rewards, 10000), label="Optimal actions")
        plt.legend()
        plt.pause(0.0001)

实质上，有三种可能的行动(第1-3条)和6种情况(装置1-6)，每种组合都有一定的CTR (点击率)和给定上下文的最佳行动(在给定装置时ctr最高的条款)。每次迭代时，随机抽取上下文，计算每个动作的回报/后悔。如果奖励为1(用户单击)，则VowpalWabbit用于学习的成本为-1，如果奖励为0，则为0(用户没有单击)。随着时间的推移，该算法被认为是为每个设备找到最好的文章。

一些结果(随着时间的推移平均奖励)：