Don Reba

Spain

Age: 31

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

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

7h
answered Markov Decision Process - reinvesting rewards
23h
comment when to apply feature selection
Why not apply machine learning to the problem?
1d
awarded Yearling
1d
awarded Yearling
1d
awarded Commentator
1d
comment Neural networks: No solutions for test data possible?
@kim366, technologyreview.com/s/541276/…
1d
awarded Editor
1d
revised Neural networks: No solutions for test data possible?
added 13 characters in body
1d
awarded Critic
1d
answered Neural networks: No solutions for test data possible?
2d
comment How can I use stanford parser in my java program for effective sentiment analysis
Is there no manual for the Stanford Parser? What's the problem?
Apr
28
awarded Enlightened
Apr
28
awarded Nice Answer
Apr
24
revised Is this a correct implementation of Q-Learning for Checkers?
added 17 characters in body
Apr
24
comment Is this a correct implementation of Q-Learning for Checkers?
@Samalot, I would not be surprised if it did not improve after a million.
Apr
24
revised Is this a correct implementation of Q-Learning for Checkers?
added 237 characters in body
Apr
24
answered Is this a correct implementation of Q-Learning for Checkers?
Apr
24
comment What's the relation between game theory and reinforcement learning?
This was educational. :)
Apr
23
comment Reinforcement Learning - How does an Agent know which action to pick?
Even Google's Atari-playing AI uses reinforcement learning with an ε-greedy policy. It gradually decreases the ε from 1.0 to 0.1 over the first million frames while learning.
Apr
23
answered Reinforcement Learning - How does an Agent know which action to pick?
1 2 3 4 5