Author Topic: Q-Learning interesting Problem  (Read 673 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: 5357
  • 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
Thoughts on the fear of AI
by DemonRaven (General AI Discussion)
Today at 03:48:00 AM
Eric Fedydurke
by Claude (Video)
October 06, 2015, 11:34:27 PM
Ivona Voice
by DemonRaven (Sound Software)
October 06, 2015, 10:47:51 PM
Way off topic but let's see what it "generates" ...;)
by Art (General Chat)
October 06, 2015, 08:59:55 PM
Friday Funny
by Claude (General Chat)
October 06, 2015, 07:59:41 PM
Chuukese Reggae (Remake)
by Claude (Video)
October 06, 2015, 03:02:11 AM
A philosophical issue
by Art (General AI Discussion)
October 05, 2015, 01:06:04 AM
Cookies and website statistics
by DemonRaven (General Project Discussion)
October 04, 2015, 11:55:33 PM
I have AI and want to show you my animation of it working.
by Mr.SecretHeavenCode (AI News )
Today at 01:16:07 AM
The top 7 innovations at risk from overzealous regulation
by Tyler (AI News )
October 06, 2015, 11:01:35 PM
The Year of CoCoRo Video #40/52: Adaptive layers water column
by Tyler (Robotics News)
October 06, 2015, 11:01:34 PM
Zignal Labs launches command center to drive social channel insights
by Tyler (AI News )
October 06, 2015, 05:00:09 PM
Robohub Digest 09/15: Big brands, and cozying up to robots
by Tyler (Robotics News)
October 06, 2015, 05:00:08 PM
Quantum computers take a leap forward after scientists build qubit logic gate on silicon chip
by Tyler (AI News )
October 06, 2015, 11:00:13 AM
Air and ground robot collaborate to map and safely navigate unknown, changing terrain
by Tyler (Robotics News)
October 06, 2015, 11:00:12 AM
How the brain recognizes objects
by Tyler (AI News )
October 06, 2015, 05:00:11 AM

Users Online

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

Most Online Today: 25. Most Online Ever: 208 (August 27, 2008, 08:36:30 AM)