DQN Space I Open-Source Game Agent Model - Freely Help You Enjoy Playing Space Invaders Game

Dqnspacei

Developed by Oleg78

This is a DQN agent model trained using the stable-baselines3 library, specifically designed for the SpaceInvadersNoFrameskip-v4 game environment.

Video Processing #Atari games #Deep Q-Learning #Frame stacking processing

Downloads 15

Release Time : 11/13/2022

Model Overview

This model is trained with the deep reinforcement learning algorithm DQN and can make decisions and take actions in the SpaceInvadersNoFrameskip-v4 game environment.

Model Features

Based on a stable reinforcement learning framework

Trained using the stable-baselines3 library, a reliable implementation framework for reinforcement learning.

Specialized for Atari games

Optimized specifically for the SpaceInvadersNoFrameskip-v4 game environment.

Pre-trained model

Provides a ready-to-use trained model for direct game testing.

Model Capabilities

Atari game decision-making

Reinforcement learning policy execution

Game environment interaction

Use Cases

Game AI

Space Invaders Game AI

Use this model as an AI player for Space Invaders.

Average reward reached 347.50 +/- 111.07

Reinforcement Learning Research

DQN Algorithm Research

Used as a reference for DQN algorithm implementation in Atari games.

🚀 Stable-Baselines3 DQN Agent for SpaceInvadersNoFrameskip-v4

This project presents a trained DQN agent for the SpaceInvadersNoFrameskip-v4 game. It leverages the stable-baselines3 library and the RL Zoo to achieve reinforcement learning goals. The RL Zoo serves as a training framework for Stable Baselines3 agents, offering hyperparameter optimization and pre - trained agents.

📊 Model Information

Property	Details
Model Type	DQN
Training Dataset	SpaceInvadersNoFrameskip-v4
Mean Reward	347.50 +/- 111.07

🚀 Quick Start

✨ Features

Trained DQN agent for the SpaceInvadersNoFrameskip-v4 game.
Utilizes the stable-baselines3 library and RL Zoo for training and deployment.

📦 Installation

The project depends on the following libraries:

RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo
SB3: https://github.com/DLR-RM/stable-baselines3
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib

💻 Usage Examples

Basic Usage

If you want to download the model and run it, you can use the following commands:

# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Oleg78 -f logs/
python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/

If you installed the RL Zoo3 via pip (pip install rl_zoo3), you can run the following commands from anywhere:

python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Oleg78 -f logs/
rl_zoo3 enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/

Advanced Usage

Training the Model

python train.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Oleg78

🔧 Technical Details

Hyperparameters

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', 500000.0),
             ('optimize_memory_usage', False),
             ('policy', 'CnnPolicy'),
             ('target_update_interval', 1000),
             ('train_freq', 4),
             ('normalize', False)])

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご