Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Appearance settings

VarunPwr/DeepRL_airsim

Open more actions menu

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Deep Reinforcement learning in AirSim

Requirements

Install AirSim and Unreal Engine 4 using the instructions from the official website. Pytorch can be installed from the instructions given here.
Other dependencies can be installed using the following line of command

pip install --user -r requirements.txt

How to Run

Train using DQN from the following command

python main.py --batch_size 32 --num_frames 10000000

Train using dueling DQN from the following command

python main.py --batch_size 32 --num_frames 10000000 --dueling

Load previously trained model to restart training

python main.py --batch_size 32 --num_frames 10000000 --load_model --model_path \path\to\model --optimizer_path \path\to\optimizer

How to modify

Change environment

Add a different environment by adding environment class in main.py

Modifying network

The network could be modified in network.py

Acknowledgements

The environment class is inspired by the works of Subin Yang

Author

Varun Pawar

About

Deep Q-learning in AirSim quadrotor environment.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

Morty Proxy This is a proxified and sanitized view of the page, visit original site.