You can deploy this model and start earning money today!

whatthehelly31/
dqn-pong

Name: dqn-pong
Availability: InStock

Views

No views yet

DQN Agent playing Pong

This is a trained DQN agent playing Pong using the stable-baselines3 library.

Usage

python

from stable_baselines3 import DQN
import gymnasium as gym
from gymnasium.wrappers import AtariPreprocessing
from stable_baselines3.common.atari_wrappers import FrameStack

# Create environment with proper preprocessing
env = gym.make("ALE/Pong-v5")
env = AtariPreprocessing(env, frame_skip=4, grayscale_obs=True, scale_obs=True)
env = FrameStack(env, 4)

# Load the model
model = DQN.load("ALE-Pong-v5.zip")

# Enjoy!
obs, _ = env.reset()
for _ in range(1000):
    action, _states = model.predict(obs, deterministic=True)
    obs, reward, terminated, truncated, info = env.step(action)
    env.render()
    if terminated or truncated:
        obs, _ = env.reset()

whatthehelly31/dqn-pong

DQN Agent playing Pong

Usage

whatthehelly31/
dqn-pong