Reinforcement Learning
stable-baselines3
Deep Q-Learning
SpaceInvadersNoFrameskip-v4
custom-implementation
Eval Results (legacy)
Instructions to use chubbyk/dqn-SpaceInvadersNoFrameskip-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- stable-baselines3
How to use chubbyk/dqn-SpaceInvadersNoFrameskip-v4 with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="chubbyk/dqn-SpaceInvadersNoFrameskip-v4", filename="{MODEL FILENAME}.zip", ) - Notebooks
- Google Colab
- Kaggle
DQN Agent for SpaceInvadersNoFrameskip-v4
This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using Stable-Baselines3.
Evaluation Results
Mean Reward: 481.00 +/- 130.28
Usage
from stable_baselines3 import DQN
from stable_baselines3.common.env_util import make_atari_env
from stable_baselines3.common.vec_env import VecFrameStack
env = make_atari_env("SpaceInvadersNoFrameskip-v4", n_envs=1)
env = VecFrameStack(env, n_stack=4)
model = DQN.load("dqn-SpaceInvadersNoFrameskip-v4.zip", env=env)
- Downloads last month
- 9
Evaluation results
- mean_reward on SpaceInvadersNoFrameskip-v4self-reported481.000