Artificial Intelligence
Brale's user avatar
Brale's user avatar
Brale's user avatar
Brale
  • Member for 5 years
  • Last seen this week
Profile Activity
Stats
2,336
reputation
64k
reached
68
answers
3
questions
Communities
View all
Badges
View all badges
1
gold badge
6
silver badges
15
bronze badges
Top tags
View all tags
109
Score
52
Posts
73
Posts %
25
Score
12
Posts
17
Posts %
24
Score
9
Posts
13
Posts %
19
Score
6
Posts
8
Posts %
17
Score
6
Posts
8
Posts %
16
Score
8
Posts
11
Posts %
Top posts
View all questions and answers
All Questions Answers
Score Newest
question
10
Why is the n-step tree backup algorithm an off-policy algorithm?
Dec 13, 2018
answer
7
Why is the state-action value function used more than the state value function?
Feb 14, 2020
answer
6
If vanishing gradients are NOT the problem that ResNets solve, then what is the explanation behind ResNet success?
Mar 18, 2020
answer
6
Why does the definition of the reward function $r(s, a, s')$ involve the term $p(s' \mid s, a)$?
Apr 14, 2020
answer
6
How do updates in SARSA and Q-learning differ in code?
Feb 9, 2019
answer
5
How does being on-policy prevent us from using the replay buffer with the policy gradients?
May 15, 2020
answer
5
Eligibility vector for softmax policy with policy gradients
Dec 5, 2019
answer
5
Why are there two versions of softmax cross entropy? Which one to use in what situation?
Oct 24, 2020
answer
4
Reinforcement Learning with long term rewards and fixed states and actions
Mar 20, 2019
answer
4
Why does is make sense to normalize rewards per episode in reinforcement learning?
Jan 25, 2019

Your privacy

By clicking “Accept all cookies”, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our Cookie Policy.