q-Taxi-v3

Q-Learning Agent playing1 Taxi-v3

This is a trained model of a Q-Learning agent playing Taxi-v3 .

Usage

import gymnasium as gym
from huggingface_sb3 import load_from_hub
import numpy as np
import pickle

# Load the model
env_name = "Taxi-v3"
model_name = "q-Taxi-v3"
model_path = load_from_hub(repo_id="ch-bz/" + model_name, filename="q-learning.pkl")
Qtable = pickle.load(open(model_path, "rb"))["qtable"]
env = gym.make("Taxi-v3", render_mode="human")
state, info = env.reset()

while True:
    action = np.argmax(Qtable[state][:])
    state, reward, terminated, truncated, info = env.step(action)
    env.render()
    
    if terminated or truncated:
        state, info = env.reset()