Artificial Intelligence
Profile Activity
Meta user
Network profile
1,818
reputation
5
26

Philip Raeisghasem

PhD student at LA Tech studying Reinforcement Learning

35
answers
5
questions
~16k
people reached
  • Ruston, LA, USA
  • philiptkd
  • Member for 2 years, 5 months
  • 244 profile views
  • Last seen Sep 12 '20 at 23:27

Communities (11)

Top network posts

We respect a laser-like focus on one topic.

Top tags (57)

Score 77
Posts 24
Posts % 60
Score 28
Posts 10
Score 21
Posts 5
Score 13
Posts 4
Score 11
Posts 6
Score 6
Posts 3
View all tags →

Top posts (40)

All Questions Answers
Votes Newest
23 What is the Bellman operator in reinforcement learning? Mar 10 '19
8 What loss function to use when labels are probabilities? Apr 14 '19
6 Which kind of prioritized experience replay should I use? May 5 '19
5 Apart from the state and state-action value functions, what are other examples of value functions used in RL? Mar 7 '19
5 Which kind of prioritized experience replay should I use? May 5 '19
5 How is the policy gradient calculated in REINFORCE? Apr 22 '19
5 Are there reinforcement learning algorithms that scale to large problems? Apr 15 '19
5 How can the $\lambda$-return be defined recursively? Apr 12 '19
5 Looking for comprehensive material on learning in mammals Mar 18 '19
5 Why isn't the ElliotSig activation function widely used? Mar 17 '19
View all questions and answers →

Badges (31)

Gold

—

Silver

5

Rarest

Bronze

26

Rarest

View all badges →

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.