Author Topic: Q-Learning interesting Problem  (Read 577 times)

binharoun_7

  • *
  • Roomba
  • Posts: 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

  • *
  • Deep Thought
  • *********************
  • Posts: 5104
  • 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 :)

 

Welcome

Please login or register.



Login with username, password and session length
Music Vids
by Claude (General Chat)
Today at 08:37:08 PM
Friday Funny
by Claude (General Chat)
Today at 08:07:26 PM
Controlling matter with sound
by Ultron (General Chat)
Today at 02:06:47 PM
Closer to 'Natural' Robots
by Ultron (General Robotics Talk)
Today at 01:33:48 PM
Robot and Buddy
by Ultron (General Robotics Talk)
Today at 01:27:20 PM
The Before & After experience
by Ultron (General Chat)
March 25, 2015, 11:32:21 PM
Fran├žois Bonneau - (parodies)
by Claude (Video)
March 25, 2015, 08:33:00 PM
Laga Savea
by Claude (General Chat)
March 25, 2015, 01:14:18 PM
Elon Musk claims artificial intelligence will treat humans like 'labradors'
by 8pla.net (AI News )
Today at 08:31:50 PM
Drones cleared to check power lines after outages
by Tyler (Robotics News)
Today at 05:00:26 PM
Facebook’s Yann LeCun Discusses Digital Companions and Artificial Intelligence (and Emotions)
by Tyler (AI News )
Today at 11:00:07 AM
Vision System Design announces 2015 Innovators Awards honorees
by Tyler (AI News )
Today at 11:00:06 AM
Intelligent robots must uphold human rights
by Tyler (AI News )
Today at 05:00:34 AM
Mobile battery life can be prolonged with system settings
by Tyler (Robotics News)
March 25, 2015, 11:00:17 PM
Robots on reins could be the 'eyes' of firefighters
by Tyler (Robotics News)
March 25, 2015, 05:01:00 PM
Why analytics is eating the world
by Tyler (AI News )
March 25, 2015, 05:01:51 AM

Users Online

31 Guests, 0 Users

Most Online Today: 52. Most Online Ever: 208 (August 27, 2008, 08:36:30 AM)

Articles