ບັນລຸເປົ້າໝາຍໄດ້ດີ ແລະ ໄວຂຶ້ນ

import numpy as np
import gymnasium as gym

env = gym.make("FrozenLake-v1", is_slippery=False)
n_s, n_a = env.observation_space.n, env.action_space.n
Q = np.zeros((n_s, n_a))
model = {}                       # (s, a) -> (r, s2, term)  ໂມເດວທີ່ຮຽນຈາກປະສົບການ
rng = np.random.default_rng(0)
gamma, alpha, eps, n_planning = 0.95, 0.5, 0.1, 20

def update(s, a, r, s2, term):
    target = r + gamma * Q[s2].max() * (not term)
    Q[s, a] += alpha * (target - Q[s, a])

for ep in range(30):
    s, _ = env.reset(seed=ep)
    done, steps = False, 0
    while not done:
        if rng.random() < eps or Q[s].max() == Q[s].min():
            a = rng.integers(n_a)
        else:
            a = int(np.argmax(Q[s]))
        s2, r, term, trunc, _ = env.step(a)
        update(s, a, r, s2, term)                  # 1) ຮຽນຈາກປະສົບການຈິງ
        model[(s, a)] = (r, s2, term)              # 2) ບັນທຶກລົງໂມເດວ
        keys = list(model)
        for _ in range(n_planning):                # 3) "ຈິນຕະນາການ" ຈາກໂມເດວ
            ps, pa = keys[rng.integers(len(keys))]
            update(ps, pa, *model[(ps, pa)])
        s, done, steps = s2, term or trunc, steps + 1
    if r == 1:
        print(f"ເກມທີ {ep:2d}: ໄປຮອດເປົ້າໝາຍໃນ {steps} ກ້າວ")