ชั่งเป้าหมายระยะสั้นและระยะยาว

import numpy as np
import gymnasium as gym

def value_iteration(P, gamma=0.99, theta=1e-10):
    n_s, n_a = len(P), len(P[0])
    V = np.zeros(n_s)
    while True:
        Q = np.zeros((n_s, n_a))
        for s in range(n_s):
            for a in range(n_a):
                for prob, s2, r, done in P[s][a]:
                    Q[s, a] += prob * (r + gamma * V[s2] * (not done))
        if np.max(np.abs(V - Q.max(axis=1))) < theta:
            break
        V = Q.max(axis=1)                 # Bellman optimality backup
    pi = Q.argmax(axis=1)                 # ນະໂຍບາຍ greedy
    return V, pi

env = gym.make("FrozenLake-v1", is_slippery=True)
V, pi = value_iteration(env.unwrapped.P)
print(np.round(V.reshape(4, 4), 3))
print("π* =", "".join("←↓→↑"[a] for a in pi))

# ທົດສອບນະໂຍບາຍ 1,000 ເກມ
wins = 0
for ep in range(1000):
    s, _ = env.reset(seed=ep)
    done = False
    while not done:
        s, r, term, trunc, _ = env.step(pi[s])
        done = term or trunc
    wins += r
print(f"ອັດຕາສຳເລັດ: {wins / 10:.1f}%")