Author Topic: Q-Learning interesting Problem  (Read 703 times)


  • *
  • 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

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!


  • *
  • Deep Thought
  • *********************
  • Posts: 5411
  • 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 - the programmers tend to hang out there more.

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



Please login or register.

Login with username, password and session length
Is it just me or ??
by DemonRaven (General Chat)
Today at 01:08:45 AM
by Data (General Chat)
November 25, 2015, 09:36:43 PM
Friday Funny
by Claude (General Chat)
November 25, 2015, 08:00:26 PM
metalanguage: a language for describing other languages
by ivan.moony (AI Programming)
November 25, 2015, 05:42:45 PM
Anyone want to buy me a christmas present
by DemonRaven (General Robotics Talk)
November 25, 2015, 12:09:34 PM
Can AI be discovered from the Bible?
by DemonRaven (General AI Discussion)
November 25, 2015, 02:31:19 AM
Twilight Zone moment
by Art (General Chat)
November 25, 2015, 01:01:15 AM
What's everyone up to ?
by DemonRaven (General Chat)
November 25, 2015, 12:43:57 AM
Car Seat Senses Your Road Rage, Offers a Massage
by Tyler (AI News )
November 25, 2015, 11:00:34 PM
The Drone Center’s Weekly Roundup: 11/23/15
by Tyler (Robotics News)
November 25, 2015, 11:00:33 PM
Why bartenders have to ignore some signals
by Tyler (AI News )
November 25, 2015, 05:00:33 PM
No, a Google car was not ticketed for going too slow (and other robocar stories)
by Tyler (Robotics News)
November 25, 2015, 05:00:33 PM
Elbot – The Cheeky Chatbot That Never Gives a Straight Answer, Goes Mobile
by DemonRaven (AI News )
November 24, 2015, 09:22:00 AM
‘Rise of the Robots’ receives Business Book of the Year award
by Tyler (Robotics News)
November 24, 2015, 05:01:11 AM
Computers can perceive image curves like artists
by Tyler (AI News )
November 23, 2015, 11:00:51 PM
The Robot Race To Hawaii Contest
by Tyler (Robotics News)
November 23, 2015, 11:00:50 PM

Users Online

13 Guests, 1 User
Users active in past 15 minutes:
[Trusty Member]

Most Online Today: 28. Most Online Ever: 208 (August 27, 2008, 08:36:30 AM)