search

Ezgii / Escaping-maze-using-RL

Escaping from a maze using Reinforcement Learning techniques.
0 stars 0 forks source link

How to make the agent run variable maze? #1

Open ShowiBin opened 1 year ago

ShowiBin commented 1 year ago

I'm working on train a agent able to run any maze map without further training. Is this code finished this? Is this task impossible?

Ezgii commented 1 year ago

Hi This code does not train the agent for any maze without further training. But I now that it is possible. I suggest that you check out "meta learning". This paper can be insightful: http://proceedings.mlr.press/v70/finn17a/finn17a.pdf

ShowiBin commented 1 year ago

thanks for your help,

Ezgii commented 1 year ago

you are welcome