Skip to main content
Artificial Intelligence
David's user avatar
David's user avatar
David's user avatar
David
  • Member for 4 years, 7 months
  • Last seen this week
Profile Activity
Stats
5,030
reputation
133k
reached
122
answers
10
questions
Communities
View all
Badges
View all badges
1
gold badge
9
silver badges
31
bronze badges
Top tags
View all tags
264
Score
107
Posts
81
Posts %
100
Score
31
Posts
23
Posts %
67
Score
23
Posts
17
Posts %
67
Score
21
Posts
16
Posts %
46
Score
10
Posts
8
Posts %
41
Score
17
Posts
13
Posts %
Top posts
View all questions and answers
answer
24
What exactly are the "parameters" in GPT-3's 175 billion parameters and how are they chosen/generated?
Jul 28, 2020
answer
11
What exactly is the advantage of double DQN over DQN?
Jul 30, 2020
answer
10
Why does the state-action value function, defined as an expected value of the reward and state value function, not need to follow a policy?
Jun 6, 2020
answer
9
What is the difference between Q-learning, Deep Q-learning and Deep Q-network?
Jan 22, 2021
answer
8
Are Q-learning and SARSA the same when action selection is greedy?
May 11, 2020
answer
7
Why do we need target network in deep Q learning?
Jul 15, 2020
answer
7
What does the notation $\mathcal{N}(z; \mu, \sigma)$ stand for in statistics?
Aug 23, 2020
answer
7
Why do we need importance sampling?
Jan 4, 2021
answer
7
Why do feedforward neural networks require the inputs to be of a fixed size, while RNNs can process variable-size inputs?
Feb 4, 2021
answer
6
How can a probability density value be used for the likelihood calculation?
Jan 8, 2021
Top network posts
View all network posts
14
Why does the design of heuristics require considerable domain knowledge?
6
Budgeted max cut heuristic