Skip to content

rouchenzi/rl-3d

Repository files navigation

gym-ultra3d

The Ultra-3D environment is a single agent domain featuring continuous state and discrete action spaces. The goal is to teach an agent to learn the shortest sequence of probe movements that would result in the capture of an optimal AP4 2D image. We use a DQN agent to explore the 3D ultrasound space, while feeding 2D cross-sections into a simple deep CNN network. The reinforcement learning makes use of the keras-rl python library, integrated with a custom implementation of OpenAI's gym environment.

To run the demo

cd RL-Ultra3D
pip3 install -r requirements.txt
python3 dqn_ultra.py --mode=test

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages