Dqn SpaceInvadersNoFrameskip V4

🚀 DQN Agent for SpaceInvadersNoFrameskip-v4

This project presents a trained DQN agent designed to play the SpaceInvadersNoFrameskip-v4 game. It leverages the stable-baselines3 library and the RL Zoo, a training framework for Stable Baselines3 reinforcement learning agents that includes hyperparameter optimization and pre-trained agents.

🔍 Model Information

🚀 Quick Start

✨ Usage (with SB3 RL Zoo)

You can use the pre - trained model with the following steps:

# Download model and save it into the logs/ folder
python -m utils.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga rushic24 -f logs/
python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/

🏋️ Training (with the RL Zoo)

If you want to train the model from scratch, use the following commands:

python train.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m utils.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga rushic24

💻 Usage Examples

📋 Hyperparameters

The following are the hyperparameters used for training the DQN agent:

OrderedDict([('batch_size', 32),
             ('buffer_size', 100000),
             ('env_wrapper',
              ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
             ('exploration_final_eps', 0.01),
             ('exploration_fraction', 0.1),
             ('frame_stack', 4),
             ('gradient_steps', 1),
             ('learning_rate', 0.0001),
             ('learning_starts', 100000),
             ('n_timesteps', 10000000.0),
             ('optimize_memory_usage', True),
             ('policy', 'CnnPolicy'),
             ('target_update_interval', 1000),
             ('train_freq', 4),
             ('normalize', False)])