Q-Learning Agent playing1 BreakoutNoFrameskip-v4
This is a trained model of a Q-Learning agent playing BreakoutNoFrameskip-v4 .
Usage
model = load_from_hub(repo_id="Arch4ngel/dqn-BreakoutNoFrameSkip-v4_cl", filename="dqn.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
Evaluation results
- mean_reward on BreakoutNoFrameskip-v4self-reported3.20 +/- 1.99