SREE064/q-Taxi-v3

Q-Learning Agent playing Taxi-v3

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

Evaluation Results

• Mean Reward: 7.56 +/- 2.71
• Baseline Requirement: >= 4.0
• Effective Score: 4.85

Usage

import pickle
import gymnasium as gym
from huggingface_hub import hf_hub_download

# Download model
model_path = hf_hub_download(repo_id="SREE064/q-Taxi-v3", filename="q-learning.pkl")
with open(model_path, "rb") as f:
    model = pickle.load(f)

env = gym.make(model["env_id"])
state, info = env.reset()
action = np.argmax(model["qtable"][state])