Skip to content
DOCXOLOGY
Share
Explore

Notes/Test

Hello, hope all is well. I have a question about a possible contract.

Here is the current state of the simulation I am interested in (this is my github: https://github.com/C20H25N30/ants/ ). It is a simulation of an ant colony, and we published this in 2021.

I am interested in some possible extensions using machine learning. Not sure which of these might be possible/interesting to you,
1. Parameter sweeping (e.g. through these: https://github.com/C20H25N30/ants/blob/main/config.py) and then doing descriptive statistics + machine learning on the outputs of each run (line 348 the ant_locations: https://github.com/C20H25N30/ants/blob/main/ants.py ).

2. Integrating this somehow with commonly-used machine learning frameworks like https://gym.openai.com/ .

3. Making the "ant" (class Ant line 11 https://github.com/C20H25N30/ants/blob/main/ants.py) a more advanced cognitive agent. Currently it implements a Markov Decision Process
Want to print your doc?
This is not the way.
Try clicking the ⋯ next to your doc name or using a keyboard shortcut (
CtrlP
) instead.