SpaceInvadersNoFrameskip-v4-2Msteps Open-Source Game Agent - Play SpaceInvadersNoFrameskip-v4 Game for Free

Spaceinvadersnoframeskip V4 2Msteps

Developed by bguan

This is a reinforcement learning agent based on the DQN algorithm, specifically designed to play the SpaceInvadersNoFrameskip-v4 game, trained using the stable-baselines3 library.

Video Processing #Atari game #Deep Q-Learning #Frame stacking

Downloads 17

Release Time : 6/12/2022

Model Overview

This model is trained using the Deep Q-Network (DQN) algorithm and can achieve good performance in the Atari game Space Invaders, with an average reward of around 550 points.

Model Features

Optimized for Atari games

Specifically optimized for Atari game environments, particularly the Space Invaders game

Stable training framework

Built on the stable-baselines3 library, providing a reliable training environment

Pre-trained model

Provides a pre-trained model that can be directly used for game testing

Model Capabilities

Atari game control

Reinforcement learning decision-making

Game state understanding

Use Cases

Game AI

Space Invaders game AI

Use this model as an AI player for the Space Invaders game

Average reward around 550 points

Reinforcement learning research

DQN algorithm performance research

Serves as an implementation case of the DQN algorithm on Atari games

🚀 DQN Agent for SpaceInvadersNoFrameskip-v4

This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4, leveraging the stable-baselines3 library and the RL Zoo to achieve high - performance reinforcement learning.

🚀 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 bguan -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 bguan

🔧 Technical Details

Hyperparameters

OrderedDict([('batch_size', 256),
             ('buffer_size', 400000),
             ('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', 2000000),
             ('optimize_memory_usage', True),
             ('policy', 'CnnPolicy'),
             ('target_update_interval', 1000),
             ('train_freq', 4),
             ('normalize', False)])

Model Metrics

Property	Details
Model Type	DQN
Mean Reward	550.00 +/- 150.17
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