Skip to main content
Artificial Intelligence
Phizaz's user avatar
Phizaz's user avatar
Phizaz's user avatar
Phizaz
  • Member for 7 years, 2 months
  • Last seen more than 2 years ago
  • Bangkok, Thailand
Profile Activity
Stats
520
reputation
15k
reached
4
answers
8
questions
Communities
View all
Badges
View all badges
This user doesn’t have any gold badges yet.
3
silver badges
13
bronze badges
Top tags
View all tags
14
Score
11
Posts
92
Posts %
9
Score
6
Posts
50
Posts %
4
Score
1
Posts
8
Posts %
4
Score
1
Posts
8
Posts %
4
Score
1
Posts
8
Posts %
3
Score
3
Posts
25
Posts %
Top posts
View all questions and answers
question
7
Why don't people use projected Bellman error with deep neural networks?
Apr 12, 2019
answer
6
Is there an alternative to the use of target network?
Mar 1, 2019
question
5
Is there an alternative to the use of target network?
Feb 27, 2019
answer
4
Expected SARSA vs SARSA in "RL: An Introduction"
Feb 27, 2019
question
3
What is a non-starving policy in reinforcement learning?
Sep 11, 2019
question
3
What are the differences between stability and convergence in reinforcement learning?
Sep 19, 2019
question
3
In DQN, updating target network every N steps or slowly update every step is better?
Feb 28, 2019
answer
3
Why don't people use projected Bellman error with deep neural networks?
Oct 9, 2019
question
3
Why they use KL divergence in Natural gradient?
Oct 30, 2019
question
2
Why overfitting is bad in DQN?
Apr 30, 2019
Top network posts
View all network posts
10
In Typescript, Is it possible to declare "type" from an existing object?
7
In Typescript, Is it possible to declare "type" from an existing object?
7
How to make "conda" download packages in parallel