DQN Pong Agent
This is a Deep Q-Learning (DQN) agent trained to play PongNoFrameskip-v4 using Stable-Baselines3.
- Environment: PongNoFrameskip-v4
- Algorithm: DQN (Deep Q-Learning)
- Framework: Stable-Baselines3
- Training steps: 100,000
Usage
from stable_baselines3 import DQN
import gym
model = DQN.load("path/to/dqn_pong_model.zip")
env = gym.make("PongNoFrameskip-v4")
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="Shreyboiii/dqn-pong", filename="{MODEL FILENAME}.zip", )