Artificial Intelligence
Sponsored by
Sponsored logo
Profile Activity
Meta user
Network profile
507
reputation
4
14

Gulzar

30 years old, Bsc graduate from Technion, Israel Institute of Technology, algorithm engineer at EPD, a cardio-mapping company acquired by Philips.

Enthusiastic about image/signal processing, and machine learning. Also about reinforcement learning for control problems.

2
answers
20
questions
~9k
people reached
  • Technion, Israel
  • noamzilo
  • Member for 1 year, 10 months
  • 29 profile views
  • Last seen 8 hours ago

Communities (30)

Top network posts

Top tags (33)

Score 1
Posts 6
Posts % 27
Score 1
Posts 2
Score 0
Posts 15
Score 0
Posts 14
Score 0
Posts 4
Score 0
Posts 3
View all tags →

Top posts (22)

All Questions Answers
Votes Newest
9 Why does is make sense to normalize rewards per episode in reinforcement learning? Jan 24 '19
6 Can TD($\lambda$) be used with deep reinforcement learning? Feb 2 '19
4 How to identify too small network in reinforcement learning? Jan 26 '19
3 Meaning of Actor Output in Actor Critic Reinforcement Learning Feb 6 '19
2 Is there a relation between the size of the neural networks and speed of convergence in deep reinforcement learning? Jan 28 '19
2 In online one step actor critic, why does the weights update become less significant as the episode progresses? Feb 12 '19
2 What information should be cached in experience replay for actor-critic? Jan 31 '19
2 Which Openai Gym environment should I use to test a Temporal Difference RL Agent? Feb 2 '19
1 Why is the reward signal normalized in openAI's REINFORCE? [duplicate] Dec 15 '18
1 When are Q values calculated in experience replay? Feb 1 '19
View all questions and answers →

Badges (18)

Gold

—

Silver

4

Rarest

Bronze

14

Rarest

View all badges →