Cross Validated
Network profile
545
reputation
2
7

Don Reba

Representative of the Holy Order in the Arkanarian Province. Bishop and Councilor of War, servant of Our Lord!

http://careers.stackoverflow.com/alexey-badalov

alexey.badalov at gmail

21
answers
0
questions
~10k
people reached
  • Vancouver, BC, Canada
  • don-reba
  • Member for 7 years, 8 months
  • 56 profile views
  • Last seen Sep 4 at 15:56

Communities (34)

Top network posts

Top tags (10)

Score 25
Posts 12
Posts % 57
Score 22
Posts 20
Score 10
Posts 3
Score 8
Posts 1
Score 8
Posts 1
Score 5
Posts 4
View all tags →

Top posts (21) All Questions Answers | Votes Newest

8 Entropy in decision tree classification Oct 2 '13
6 Updating q-values in q-learning Mar 27 '17
4 How to calculate $max_{\alpha}Q(S',a')$ in q learning? Oct 6 '16
3 Why is there always at least one policy that is better than or equal to all other policies? Apr 17 '16
2 Friend or Foe Q Learning Algorithm Q-Value Update Jul 13 '15
2 Reinforcement learning algorithms dependency on the initial state Jul 20 '16
2 Meaning of 'compute' in the following statement Dec 15 '15
1 relationship between the policy and the reward in reinforcement learning Mar 7 '16
1 Q-Learning with mostly 0 reward Mar 26 '16
1 Why do we use expectation in reinforcement learning? Jul 22 '16
View all questions and answers →

Badges (9)

Gold

—

Silver

2

Rarest

Bronze

7

Rarest

View all badges →