SyntaxTheRed/dqn-SpaceInvadersNoFrameskip-v4
015
1---2library_name: stable-baselines33tags:4- SpaceInvadersNoFrameskip-v45- deep-reinforcement-learning6- reinforcement-learning7- stable-baselines38model-index:9- name: DQN10 results:11 - task:12 type: reinforcement-learning13 name: reinforcement-learning14 dataset:15 name: SpaceInvadersNoFrameskip-v416 type: SpaceInvadersNoFrameskip-v417 metrics:18 - type: mean_reward19 value: 495.50 +/- 139.3520 name: mean_reward21 verified: false22---23 24# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**25This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**26using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)27and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).28 29The RL Zoo is a training framework for Stable Baselines330reinforcement learning agents,31with hyperparameter optimization and pre-trained agents included.32 33## Usage (with SB3 RL Zoo)34 35RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>36SB3: https://github.com/DLR-RM/stable-baselines3<br/>37SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib38 39Install the RL Zoo (with SB3 and SB3-Contrib):40```bash41pip install rl_zoo342```43 44```45# Download model and save it into the logs/ folder46python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga SyntaxTheRed -f logs/47python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/48```49 50If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:51```52python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga SyntaxTheRed -f logs/53python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/54```55 56## Training (with the RL Zoo)57```58python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/59# Upload the model and generate video (when possible)60python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga SyntaxTheRed61```62 63## Hyperparameters64```python65OrderedDict([('batch_size', 32),66 ('buffer_size', 100000),67 ('env_wrapper',68 ['stable_baselines3.common.atari_wrappers.AtariWrapper']),69 ('exploration_final_eps', 0.01),70 ('exploration_fraction', 0.1),71 ('frame_stack', 4),72 ('gradient_steps', 1),73 ('learning_rate', 0.0001),74 ('learning_starts', 100000),75 ('n_timesteps', 1000000.0),76 ('optimize_memory_usage', False),77 ('policy', 'CnnPolicy'),78 ('target_update_interval', 1000),79 ('train_freq', 4),80 ('normalize', False)])81```82 83# Environment Arguments84```python85{'render_mode': 'rgb_array'}86```87 