Can anyone help me to code the Q-learning and SARSA in python? The file (the env

Question

Can anyone help me to code the Q-learning and SARSA in python? The file (the environment) is given and we just need to fill out the core algorithm.

ql sarsa.py UNREGISTERED ql sarsa.py 6 import gym 7 import time 8 from gym.wrappers import Monitor 9 from taxi_envs import * 10 12 def QLearning(env, num_episodes, gamma, 1r, e): 13 14 15 16 17 18 19 20 21 "Imp Lement the Q-learning algorithm following the epsilon-greedy exploration. Update Q at the end of every episode. Parameters env: gym.core.Environment num_episodes: int gamma: float Learning_rate: float e: float Environment to compute Q function Number of episodes of training. Discount factor. Learning rate. Epsilon value used in the epsilon-greedy method. 23 24 25 26 27 28 29 30 31 32 Returns p.array An array of shape lenv.ns x env.nA] representing state, action values 34 35 36 37 38 39 40 41 42 43 def SARSA(env, num_episodes, gamma, lr, e): YOUR CODE return np.zeros( (env.nS, env.nA)) Line 1, Column 1 Spaces:2 Python

Explanation / Answer

----------------------------------------------------------------------------------------------------------

SARSA :

Related Questions

Navigate

• Browse (All)
• Browse C
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.