Author Topic: Q-Learning interesting Problem  (Read 639 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: 5266
  • 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
Friday Funny
by Claude (General Chat)
August 01, 2015, 10:43:37 PM
Robotics and Beyond: Machine Future
by Claude (General Chat)
August 01, 2015, 09:23:15 AM
Short Documentary: Elon Musk
by (Graphics and Video Software)
July 31, 2015, 11:41:49 PM
Wordnet or similar needed
by (AI Programming)
July 31, 2015, 10:50:24 PM
Beginners topics and resources
by Freddy (General Project Discussion)
July 31, 2015, 09:39:08 PM
Animal Intelligence - Ants.
by ivan.moony (General Chat)
July 30, 2015, 06:06:28 PM
More intelligent, than wind
by ranch vermin (General Chat)
July 30, 2015, 01:42:19 PM
A Plan
by Don Patrick (Future of AI)
July 29, 2015, 05:41:48 PM
The Year of CoCoRo Video #30/52: Combined scenario number one
by Tyler (Robotics News)
August 01, 2015, 11:01:18 PM
Channel 4 renews Humans for second series ahead of season finale
by (AI News )
August 01, 2015, 05:51:09 PM
Which paintings were the most creative of their time? An algorithm may hold the answers
by Tyler (AI News )
August 01, 2015, 05:00:32 PM
Is all the hype about drone commercialization clouding our judgement?
by Tyler (Robotics News)
August 01, 2015, 05:00:31 PM
The Drone Center’s Weekly Roundup: 7/27/15
by Freddy (Robotics News)
August 01, 2015, 12:13:42 PM
Are Internet-connected devices eavesdropping on our conversations?
by Tyler (AI News )
August 01, 2015, 11:02:55 AM
#IJCAI15 brings together leading researchers in AI
by Tyler (Robotics News)
August 01, 2015, 11:02:54 AM
Automated Vehicles Symposium recap (Part 2)
by Tyler (Robotics News)
July 31, 2015, 11:00:06 PM

Users Online

22 Guests, 0 Users

Most Online Today: 26. Most Online Ever: 208 (August 27, 2008, 08:36:30 AM)