DQN - BeamRiderNoFrameskip-v4 Open-Source Game Model - Free Deployment for Smooth Atari Gameplay

Dqn BeamRiderNoFrameskip V4

Developed by sb3

This is a reinforcement learning model based on the DQN algorithm, specifically designed for the Atari game environment BeamRiderNoFrameskip-v4.

Video Processing #Atari game control #Deep Q-Network #Reinforcement learning training

Downloads 169

Release Time : 6/2/2022

Model Overview

The model is trained using the Deep Q-Network (DQN) algorithm and can make intelligent decisions in the BeamRider game environment, achieving an average reward of 4777 points.

Model Features

Specialized for Atari games

Optimized specifically for the Atari game environment BeamRiderNoFrameskip-v4

Stable training

Implemented using the stable-baselines3 library, ensuring reliable training

Efficient learning

Improves learning efficiency through techniques like experience replay and target networks

Model Capabilities

Game decision-making

Reinforcement learning

Atari game control

Use Cases

Game AI

BeamRider game AI

Implements automatic game control in BeamRider

Average reward of 4777.20 points

Reinforcement learning research

DQN algorithm research

Can serve as a benchmark model for DQN algorithm research

🚀 Stable-Baselines3 DQN for BeamRiderNoFrameskip-v4

This project presents a trained DQN agent for the BeamRiderNoFrameskip-v4 environment using the Stable-Baselines3 library and the RL Zoo, offering a practical solution for deep reinforcement learning tasks.

🚀 Quick Start

This is a trained model of a DQN agent playing BeamRiderNoFrameskip-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 rl_zoo3.load_from_hub --algo dqn --env BeamRiderNoFrameskip-v4 -orga sb3 -f logs/
python enjoy.py --algo dqn --env BeamRiderNoFrameskip-v4  -f logs/

Advanced Usage

python train.py --algo dqn --env BeamRiderNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env BeamRiderNoFrameskip-v4 -f logs/ -orga sb3

🔧 Technical Details

Hyperparameters

OrderedDict([('batch_size', 32),
             ('buffer_size', 10000),
             ('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)])

Performance Metrics

Property	Details
Model Type	DQN
Training Data	BeamRiderNoFrameskip-v4
Mean Reward	4777.20 +/- 2013.79

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