Artificial Intelligence
Profile Activity
Meta user
Network profile
412
reputation
8

dato nefaridze

I like solving hard problems. Also, I like math, now I am focusing on developing Ai systems. In particular, I am interested in reinforcement learning. If you want to make research in this filed or in general in AI, or in math, then I am ready to help you. Feel free to contact me. my Gmail is:davit.neparidze402@ens.tsu.edu.ge.

please connect me if you can help me to advance my career(job suggestion, research suggestion, project suggestion, etc)

0
answers
19
questions
~1k
people reached
  • Tbilisi
  • Member for 3 months
  • 59 profile views
  • Last seen Aug 1 at 20:32

Communities (12)

Top network posts

We respect a laser-like focus on one topic.

Top tags (22)

Score 0
Posts 14
Posts % 74
Score 0
Posts 12
Score 0
Posts 10
Score 0
Posts 3
Score 0
Posts 3
Score 0
Posts 3
View all tags →

Top posts (19)

All Questions Answers
Votes Newest
4 Is there any good reference for double deep Q-learning? May 28
3 What happens if the opponent doesn't play optimally in minimax? May 4
3 What does it mean to parameterise a policy in policy gradient methods? May 6
2 How to train a reinforcement learning agent from raw pixels? Jun 5
2 How should I decay $\epsilon$ in Q-learning? May 28
2 Is the PyTorch official tutorial really about Q-learning? May 24
1 Why do we need target network in deep Q learning? [duplicate] Jul 15
1 How to implement RAM versions of Atari games Jun 6
1 How to predict Q-values based on stack of frames Jun 5
1 Are there any good tutorials about training RL agent from raw pixels using PyTorch? Jun 3
View all questions and answers →

Badges (8)

Gold

—

Silver

—

Bronze

8

Rarest