MATLAB Answers

Reinforcement Learning Toolbox RAM increment

19 views (last 30 days)
Tech Logg Ding
Tech Logg Ding on 22 Dec 2020
Answered: Gaurav Garg on 29 Dec 2020
When I am running trainings using the Reinforcement Learning Toolbox, I noticed that the RAM usage increases significantly as the number of trainining episodes increases. Why is this happening?

  0 Comments

Sign in to comment.

Answers (1)

Gaurav Garg
Gaurav Garg on 29 Dec 2020
Hi Tech,
The RAM utilization is expected to increase significantly.
This is because there are multiple number of complex mathematical calculation (e.g. matrix multiplications, matrix inverses, activation function calculation, calculation of gradients) needed to train/test any deep neural network.
Having said that, you can run the trainings on a GPU, which would not only not use RAM, but also increase the speed of training (since, GPUs are best fit for such jobs). You can look at an example on how to train RL netowrks on GPU here.

  0 Comments

Sign in to comment.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!