Author Topic: Q-Learning interesting Problem  (Read 658 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: 5330
  • 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
True street paris
by Claude (Video)
Today at 12:39:09 AM
1024 bits virtual ram
by (AI Programming)
Today at 12:38:08 AM
Music Vids
by Data (General Chat)
September 03, 2015, 07:31:26 PM
The Bot Libre iOS, iPhone, iPad SDK is now open source
by DemonRaven (General Project Discussion)
September 03, 2015, 04:18:16 PM
Non expert development of expert systems?
by (General Project Discussion)
September 03, 2015, 04:17:52 PM
Being difficult lol
by ranch vermin (Bot Conversations)
September 03, 2015, 03:14:30 PM
Here is a speech
by Claude (Video)
September 02, 2015, 03:56:53 PM
What language for a thinkbot
by ivan.moony (AI Programming)
September 02, 2015, 12:16:07 PM
Price wars: Counting the cost of drones, planes and satellites
by Tyler (Robotics News)
September 03, 2015, 05:00:04 PM
Robots can learn from their mistakes in real-time
by Tyler (AI News )
September 03, 2015, 11:00:26 AM
Creating the voice behind Jibo
by Tyler (Robotics News)
September 03, 2015, 11:00:26 AM
Coming of age: Clearpath’s Ryan Gariepy on growing a robotics startup
by ranch vermin (Robotics News)
September 03, 2015, 05:06:05 AM
Tech gadgets for cyclists provide directions, theft protection
by Tyler (AI News )
September 03, 2015, 05:00:20 AM
Robotics and AI prominent in MIT’s annual 35 Innovators Under 35
by Tyler (Robotics News)
September 03, 2015, 05:00:19 AM
#RobotLaunch2015 Finals announced, plus final round of Readers Pick
by Tyler (Robotics News)
September 02, 2015, 11:00:12 PM
Qualcomm Brings Artificial Intelligence to Smartphone Security
by Tyler (AI News )
September 02, 2015, 05:00:45 PM

Users Online

26 Guests, 0 Users

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