Skip to main content
Share Your Experience: Take the 2024 Developer Survey
dato nefaridze's user avatar
dato nefaridze's user avatar
dato nefaridze's user avatar
dato nefaridze
  • Member for 4 years, 1 month
  • Last seen more than a month ago
  • Tbilisi
7 votes
2 answers
1k views

Is there any good reference for double deep Q-learning?

6 votes
2 answers
447 views

Why don't we use auto-encoders instead of GANs?

5 votes
1 answer
4k views

Why do we need target network in deep Q learning? [duplicate]

5 votes
1 answer
3k views

What happens if the opponent doesn't play optimally in minimax?

4 votes
1 answer
966 views

What does it mean to parameterise a policy in policy gradient methods?

4 votes
2 answers
7k views

How to calculate the distance between the camera and an object using Computer Vision?

4 votes
1 answer
301 views

Why do we sample vectors from a standard normal distribution for the generator?

4 votes
1 answer
1k views

How does Mask R-CNN automatically output a different number of objects on the image?

4 votes
1 answer
2k views

How should I decay $\epsilon$ in Q-learning?

3 votes
0 answers
125 views

Why shouldn't batch normalisation layers be learnable during fine-tuning?

3 votes
1 answer
2k views

What is generalized policy iteration?

3 votes
1 answer
6k views

How and when should we update the Q-target in deep Q-learning?

2 votes
1 answer
109 views

Is the PyTorch official tutorial really about Q-learning?

2 votes
1 answer
111 views

Why can't DQN be used for self-driving cars?

2 votes
1 answer
63 views

Do we have two Q-learning update formulas?

2 votes
1 answer
68 views

How to predict Q-values based on stack of frames

2 votes
1 answer
1k views

How to train a reinforcement learning agent from raw pixels?

2 votes
1 answer
325 views

How to implement RAM versions of Atari games

2 votes
0 answers
336 views

How to prevent deep Q-learning algorithms to overfit?

2 votes
1 answer
3k views

Why do we use the softmax instead of no activation function?

1 vote
1 answer
215 views

How can imitation learning data be collected?

1 vote
1 answer
901 views

What is a RAM state in the gym's breakout-ram environment?

1 vote
2 answers
137 views

Are there any good tutorials about training RL agent from raw pixels using PyTorch?

1 vote
1 answer
2k views

Can we increase the speed of training a reinforcement learning algorithm?

1 vote
2 answers
93 views

What kinds of techniques do autopilots of autonomous cars use?

1 vote
0 answers
135 views

When does Monte Carlo linear function approximation converge?

0 votes
0 answers
125 views

How to calculate the attention loss in the paper "Tell Me Where to Look: Guided Attention Inference Network"?

0 votes
0 answers
21 views

Book suggestion about deploying real deep learning models in real world

0 votes
1 answer
32 views

How to build a custom morphological analyser for translation system

0 votes
1 answer
194 views

What are the mathematical prerequisites needed to understand research papers on neural networks? [closed]