search

albertpumarola / QLearning-NAO_plays_Agario

ROS compatible reinforcement learning algorithm based on Q-Learning that enables a NAO robot play the Agar.io game
MIT License
24 stars 2 forks source link

Some Queries #1

Open ParthaEth opened 8 years ago

ParthaEth commented 8 years ago

Hi, First of all thanks for the great work. I want to deploy deep learning with combination of RNNs and DNNs. I saw that you control the bot by moving the mouse directly. I was wondering how you get the state of the cell? I mean current size, other cells that are around and location of food? 

Especially how do you communicate between javascript and c++, Is there a webSocet?

Would not be so bad to work together I guess. :)
albertpumarola commented 8 years ago

Hi, Thanks. The thing is that this is a project where a Nao robot must be able to play the game by its own. In other words, it is not allowed to read directly information from the game. Only computer vision algorithm where used.