Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
en:projects:details:rl09 [2009/06/05 09:42]
masoud
en:projects:details:rl09 [2011/03/07 16:09]
masoud
Line 1: Line 1:
-===== Reinforcement Learning Competition ===== 
- 
- 
- 
-[[http://​2009.rl-competition.org/​|RL competition]] is a competition organized by [[http://​www.cs.mcgill.ca/​~icml2009/​|International Conference on Machine Learning (ICML)]] committee to provide a platform for comparing the performance of Reinforcement Learning ​ 
-methods on a suite of challenging [[http://​2009.rl-competition.org/​domains.php|domains]] such as balancing a two-jointed virtual gymnast or controling a helicopter which is attempting to stably hover. ​ 
-Although the deadline for 2009 competition has already passed you may be able to participate to 2010 competition. Selected participant will be able to present their work at ICML. Note that you don't need to develop your own RL algorithm, you can start implementing an existing method and then try to improve it. The proportion of theoretical and empirical (programming,​ simulation) work in this project is 60-40 percent. ​ 
- 
-Requirement:​ 
-  * Good programming skill  
-  * Interest in AI and competition! 
-What will you learn 
-  * [[http://​en.wikipedia.org/​wiki/​Reinforcement_learning|Reinforcement learning]] 
-  * [[http://​en.wikipedia.org/​wiki/​Markov_decision_process|Markov decision processes]] 
-  * Optimizing your code to improve performance 
- 
- 
 ---- dataentry project ---- ---- dataentry project ----
 title :  Reinforcement Learning Competition ​ title :  Reinforcement Learning Competition ​
 contactname:​ Masoud Alipour contactname:​ Masoud Alipour
-contactmail_mail:​ masoud ​[dot] alipour ​[at] epfl [dot] ch+contactmail_mail:​ masoud.alipour@epfl.ch
 contacttel: 021 6937529 contacttel: 021 6937529
 contactroom:​ BC 150 contactroom:​ BC 150
Line 25: Line 8:
 status : available status : available
 created_dt : 2009-06-03 created_dt : 2009-06-03
-taken_dt :  ​+taken_dt :  ​2010-12-01
 completed_dt :  completed_dt : 
 by :  by : 
Line 34: Line 17:
 ---- ----
  
 +[[http://​2009.rl-competition.org/​|RL competition]] is a competition organized by [[http://​www.cs.mcgill.ca/​~icml2009/​|International Conference on Machine Learning (ICML)]] committee to provide a platform for comparing the performance of Reinforcement Learning ​
 +methods on a suite of challenging [[http://​2009.rl-competition.org/​domains.php|domains]] such as balancing a two-jointed virtual gymnast or controling a helicopter which is attempting to stably hover. ​
 +Although the deadline for 2009 competition has already passed you may be able to participate to 2010 competition. Selected participant will be able to present their work at ICML. Note that you don't need to develop your own RL algorithm, you can start implementing an existing method and then try to improve it. The proportion of theoretical and empirical (programming,​ simulation) work in this project is 60-40 percent. ​
 +
 +Requirement:​
 +  * Good programming skill 
 +  * Interest in AI and competition!
 +What will you learn
 +  * [[http://​en.wikipedia.org/​wiki/​Reinforcement_learning|Reinforcement learning]]
 +  * [[http://​en.wikipedia.org/​wiki/​Markov_decision_process|Markov decision processes]]
 +  * Optimizing your code to improve performance