Downloads · 30 days
0
muhrivandysetiawan/q-Taxi-v3-optuna
q-Taxi-v3-optuna is a reinforcement learning model from muhrivandysetiawan. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product.
Trained from scratch with pure NumPy Q-Learning. Part of a 12-project Deep RL portfolio.
Downloads · 30 days
0
Access
Public
Updated Apr 9, 2026
Repo size
983 KB
Likes
0
Public
Click a slice to open those files.
.mp4115 KB · 47%
From the Hugging Face model README
Trained from scratch with pure NumPy Q-Learning. Part of a 12-project Deep RL portfolio.
Mean reward: 7.50 +/- 2.63
model = load_from_hub(
repo_id="muhrivandysetiawan/q-Taxi-v3-optuna",
filename="q-learning.pkl"
)
env = gym.make(model["env_id"])
Q(s,a) ← Q(s,a) + α[r + γ·max Q(s',a') - Q(s,a)]
Project 2/12 — HuggingFace Deep RL Curriculum Author: muhrivandysetiawan