Q-Learning interesting Problem

  • 1 Replies
  • 1828 Views
*

binharoun_7

  • Roomba
  • *
  • 1
Q-Learning interesting Problem
« on: November 14, 2013, 10:03:58 am »
Hello everyone, i have just started to study Learning and see the possibilities of using Learning to solve my problem.

Problem: I am supposed to detect a certain combination of data, i have four matrices that acts as an input to my system, i have already categorised the inputs ( each input can either be Low (L) , or High (H) ). I need to detect certain types of input for example LLLH, LLHH, HHHH etc

NOTE:
1)LLLH means the first input in L, second input is L, third input is L and the fourth input is H!
2)I have labelled each type of input type as state, for example LLLL is state 1, LLLH is state 2, so on.

What i have studied in Learning is that most of the time you have one goal (only one state as a goal) which makes it easier for the agent to learn and create the Q-matrix from the R-matrix . Now in my problem i have many goal ( many states act as goal and need to be detected). I don't know how to design the states, how to create the Reward-matrix by having many goals and how the agent will learn. Can you please help me how can i use Learning in this kind of situation. Taking into account i have like 16 goals in 20+ states!

*

Freddy

  • Administrator
  • **********************
  • Colossus
  • *
  • 6831
  • Mostly Harmless
Re: Q-Learning interesting Problem
« Reply #1 on: November 15, 2013, 04:52:26 pm »
Not something I know about. I can usually think of someone to ask but I draw a blank with this one.

Maybe you could try www.chatbots.org - the programmers tend to hang out there more.

I just wanted to say welcome too, so welcome :)

 


less than one-shot learning
by ivan.moony (AI News )
October 26, 2020, 07:45:25 am
Scavengers by Improbable
by MikeB (AI News )
October 20, 2020, 06:51:05 am
Sony Patent Suggests PS5 Will Have a Chatbot Feature
by MikeB (AI News )
October 19, 2020, 09:32:40 am
efficiency breakthrough via mathematics
by infurl (AI News )
October 14, 2020, 09:47:44 am
deep drone
by infurl (Robotics News)
October 13, 2020, 03:08:39 am
cerebellum much more important than previously thought
by infurl (AI News )
October 13, 2020, 03:06:29 am
electronic neurons
by Hopefully Something (AI News )
October 02, 2020, 12:06:39 am
New model beats GPT3
by LOCKSUIT (AI News )
October 01, 2020, 11:54:25 am

Users Online

169 Guests, 0 Users

Most Online Today: 174. Most Online Ever: 528 (August 03, 2020, 06:16:11 am)

Articles