ปรับปรุงพฤติกรรมของ agent

import numpy as np
import gymnasium as gym

env = gym.make("FrozenLake-v1", is_slippery=True)
n_s, n_a = env.observation_space.n, env.action_space.n
Q = np.zeros((n_s, n_a))
rng = np.random.default_rng(0)
gamma, alpha = 0.99, 0.1
n_episodes = 20000

for ep in range(n_episodes):
    eps = max(0.01, 1.0 - ep / (0.8 * n_episodes))     # epsilon ຫຼຸດລົງເລື້ອຍໆ
    s, _ = env.reset(seed=ep)
    done = False
    while not done:
        a = rng.integers(n_a) if rng.random() < eps else int(np.argmax(Q[s]))
        s2, r, term, trunc, _ = env.step(a)
        target = r + gamma * Q[s2].max() * (not term)    # off-policy: ໃຊ້ max
        Q[s, a] += alpha * (target - Q[s, a])
        s, done = s2, term or trunc

pi = Q.argmax(axis=1)
wins = 0
for ep in range(1000):
    s, _ = env.reset(seed=100000 + ep)
    done = False
    while not done:
        s, r, term, trunc, _ = env.step(pi[s])
        done = term or trunc
    wins += r
print("π =", "".join("←↓→↑"[a] for a in pi))
print(f"ອັດຕາສຳເລັດ: {wins / 10:.1f}%")