ชั่งการสำรวจและการใช้ประโยชน์

import numpy as np

rng = np.random.default_rng(0)
true_means = rng.normal(0, 1, size=10)     # ເຄື່ອງ slot 10 ເຄື່ອງ (ບໍ່ຮູ້ຄ່າຈິງ)

def run(strategy, steps=1000):
    Q, N, total = np.zeros(10), np.zeros(10), 0.0
    for t in range(1, steps + 1):
        a = strategy(Q, N, t)
        r = rng.normal(true_means[a], 1)
        N[a] += 1
        Q[a] += (r - Q[a]) / N[a]          # ຄ່າສະເລ່ຍແບບ incremental
        total += r
    return total / steps

def epsilon_greedy(Q, N, t, eps=0.1):
    return rng.integers(10) if rng.random() < eps else int(np.argmax(Q))

def ucb(Q, N, t, c=2.0):
    if (N == 0).any():
        return int(np.argmin(N))           # ລອງທຸກເຄື່ອງກ່ອນ
    return int(np.argmax(Q + c * np.sqrt(np.log(t) / N)))

print(f"ຄ່າສູງສຸດທີ່ເປັນໄປໄດ້ : {true_means.max():.3f}")
print(f"greedy (eps=0)        : {run(lambda Q, N, t: epsilon_greedy(Q, N, t, 0)):.3f}")
print(f"epsilon-greedy (0.1)  : {run(epsilon_greedy):.3f}")
print(f"UCB                   : {run(ucb):.3f}")