RL

Developed by skyline22

This is a reinforcement learning model based on the DQN algorithm, specifically designed for training and gameplay in the SpaceInvadersNoFrameskip-v4 game environment.

Video Processing #Atari Game Reinforcement Learning #Deep Q-Network #High Frame Rate Optimization

Downloads 20

Release Time : 6/17/2022

Model Overview

The model is trained using the stable-baselines3 library and the RL Zoo framework, capable of playing Space Invaders and achieving a certain level of gameplay proficiency.

Model Features

Atari Game Specialization

Optimized specifically for the Atari game environment SpaceInvadersNoFrameskip-v4.

Stable Training Framework

Based on stable-baselines3 and RL Zoo framework, providing a reliable training environment.

Efficient Learning

Through deep reinforcement learning algorithms, the model can autonomously learn game strategies.

Model Capabilities

Atari Game Control

Autonomous Game Strategy Learning

Real-time Decision Making

Use Cases

Game AI

Space Invaders Game AI

Acts as an AI player for the Space Invaders game.

Average reward 607.00±156.27

Reinforcement Learning Research

DQN Algorithm Research

Used for studying the performance of Deep Q-Networks in game environments.

🚀 DQN Agent for SpaceInvadersNoFrameskip-v4

This is a trained DQN agent for the SpaceInvadersNoFrameskip-v4 game, leveraging the stable-baselines3 library and the RL Zoo.

🚀 Quick Start

This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the stable-baselines3 library and the RL Zoo. The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

📦 Installation

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

# Download model and save it into the logs/ folder
python -m utils.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga skyline22 -f logs/
python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/

Advanced Usage

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 skyline22

🔧 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', 10000000.0),
             ('optimize_memory_usage', True),
             ('policy', 'CnnPolicy'),
             ('target_update_interval', 1000),
             ('train_freq', 4),
             ('normalize', False)])

Model Performance

Property	Details
Model Type	DQN
Mean Reward	607.00 +/- 156.27
Task	Reinforcement Learning
Dataset	SpaceInvadersNoFrameskip-v4

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