Pythonで学ぶマルコフ連鎖と探索・活用のトレードオフ

import random

# Markov chain: tomorrow's weather depends only on today's.
transitions = {"sunny": {"sunny": 0.8, "rainy": 0.2}, "rainy": {"sunny": 0.4, "rainy": 0.6}}
dist = {"sunny": 1.0, "rainy": 0.0}
for day in range(1, 4):
    dist = {s: sum(dist[p] * transitions[p][s] for p in dist) for s in dist}
    print(f"day {day}:", {s: round(v, 3) for s, v in dist.items()})

# Epsilon-greedy bandit: usually pick the best arm so far, sometimes explore.
random.seed(1)
true_payouts = [0.3, 0.7]
counts, totals = [0, 0], [0.0, 0.0]
epsilon = 0.1
for _ in range(500):
    if random.random() < epsilon or 0 in counts:
        arm = random.randrange(2)                                  # explore
    else:
        arm = max(range(2), key=lambda a: totals[a] / counts[a])  # exploit
    reward = 1 if random.random() < true_payouts[arm] else 0
    counts[arm] += 1
    totals[arm] += reward
print("pulls per arm:", counts)
print("estimated payouts:", [round(t / c, 2) for t, c in zip(totals, counts)])