MRL - 4

실제 적용하면 실패확률이 커진다.

 

이에대한 대안으로 Q의 업데이트 부분의 일부만 이용하여 처리한다.

 

 

 

기존 알고리즘에 레이트처리를 양쪽에 하는것!!

 

 

 

 

 

---

실습예제

 

import gym
import numpy as np
import matplotlib.pyplot as plt


env = gym.make('FrozenLake-v0')

Q = np.zeros([env.observation_space.n, env.action_space.n])

learning_rate = .85
dis = .99
num_episodes = 2000

rList = []
for i in range(num_episodes):
    # Reset environment and get first new observation
    state = env.reset()
    rAll = 0
    done = False

    while not done:

        action = np.argmax(Q[state, :] + np.random.randn(1, env.action_space.n) / (i + 1))

        # Get new state and reward from environment
        new_state, reward, done, _ = env.step(action)

        # Update Q-Table with new knowledge using learning rate
        Q[state, action] = (1-learning_rate) * Q[state,action] \
                           + learning_rate*(reward + dis * np.max(Q[new_state, :]))

        rAll += reward
        state = new_state

    rList.append(rAll)

print("Score over time: " + str(sum(rList) / num_episodes))
print("Final Q-Table Values")
print(Q)
plt.bar(range(len(rList)), rList, color="blue")
plt.show()