Artificial Intelligence
Sponsored by
Sponsored logo
Profile Activity
Meta user
Network profile
1,674
reputation
1
2
10

Brale

Apparently, this user prefers to keep an air of mystery about them.

55
answers
3
questions
~14k
people reached
  • Member for 1 year, 10 months
  • 115 profile views
  • Last seen 17 hours ago

Communities (9)

Top network posts

We respect a laser-like focus on one topic.

Top tags (60)

Score 74
Posts 43
Posts % 74
Score 16
Posts 9
Score 15
Posts 5
Score 14
Posts 8
Score 13
Posts 6
Score 12
Posts 5
View all tags →

Top posts (58)

All Questions Answers
Votes Newest
5 Formula for expected rewards for state–action–next-state triples as a three-argument function Apr 14
5 Why is the state-action value function used more than the state value function? Feb 14
5 Eligibility vector for softmax policy with policy gradients Dec 5 '19
4 Why am I getting the incorrect value of lambda? May 20 '19
4 A few questions regarding the difference between policy iteration and value iteration Mar 6 '19
4 How do updates in SARSA and Q-learning differ in code? Feb 9 '19
4 Why is the n-step tree backup algorithm an off-policy algorithm? Dec 13 '18
3 How does being on-policy prevent us from using the replay buffer with the policy gradients? May 15
3 What is the intuition behind the TD(0) equation with average reward, and how is it derived? Dec 31 '19
3 DQN regarding fitting off actions Sep 18 '19
View all questions and answers →

Badges (13)

Gold

1

Rarest

Silver

2

Rarest

Bronze

10

Rarest

View all badges →