Hottest Questions Today

1

vote

1

answer

21

views

Why does TD Learning require Markovian domains?

modified 3 hours ago Neil Slater 14.1k

0

votes

0

answers

16

views

How to combine two differently equally important signals into the reward function, that have different scales?

deep-rl rewards modeling-rewards

modified 6 hours ago tmaric 290

1

vote

1

answer

22

views

Why are state-values alone not sufficient in determining a policy (without a model)?

reinforcement-learning monte-carlo model-free

modified 9 hours ago Neil Slater 14.1k

0

votes

0

answers

13

views

How to develop a model to detect a point crossed a line?

computer-vision

asked 15 hours ago ajayramesh 101

3

votes

0

answers

20

views

Why is the reward in reinforcement learning always a scalar?

reinforcement-learning rewards

modified 20 hours ago nbro 18.9k

1

vote

1

answer

25

views

Why is the optimal policy for an infinite horizon MDP deterministic?

reinforcement-learning markov-decision-process

answered yesterday harwiltz 561

1

vote

0

answers

14

views

How to overfit GANs with a single image

generative-adversarial-networks overfitting

asked yesterday ArunJose_Intel 111

0

votes

0

answers

32

views

Is it a good idea to change the learning rate at each training step as a function of the loss?

machine-learning learning-rate

modified yesterday nbro 18.9k

1

vote

0

answers

13

views

Keras model accuracy not improving beyond threshold

deep-learning tensorflow keras recurrent-neural-networks accuracy

modified 4 hours ago Jacob Hreha - NOAA Affiliate 11

0

votes

0

answers

15

views

What is the state-of-the-art algorithm for neural style transfer?

deep-learning computer-vision deep-neural-networks image-processing image-generation

asked yesterday DeepNet 1

2

votes

0

answers

27

views

Would a different learning rate for every neuron and layer mitigate or solve the vanishing gradient problem?

deep-learning backpropagation activation-function learning-rate vanishing-gradient-problem

modified yesterday nbro 18.9k

0

votes

1

answer

20

views

How do I classify whether a document is legal or not given a set of keywords that appear only in legal documents?

machine-learning classification

answered 3 hours ago Zhengyang SONG 1

1

vote

0

answers

13

views

Can I resize my images after labeling them?

object-detection object-recognition data-preprocessing

asked yesterday Ali KHalili 55

0

votes

2

answers

32

views

Is there a neural network that accepts both the current input and previous output?

neural-networks python keras recurrent-neural-networks

modified yesterday piotor 1

0

votes

1

answer

39

views

How much computing power does it cost to run GPT-3?

gpu gpt

answered yesterday hal9000 56

3

votes

1

answer

63

views

Comparing the derivation of the Deterministic Policy Gradient Theorem with the standard Policy Gradient Theorem

reinforcement-learning policy-gradients

modified yesterday David Ireland 1,493

0

votes

0

answers

18

views

Local Search vs K-means Clustering

k-means local-search

asked yesterday KGhatak 143

0

votes

0

answers

12

views

Limbs for PAFs in OpenPose

neural-networks convolutional-neural-networks research papers

modified yesterday ADA 113

3

votes

2

answers

90

views

What are some best practices when trying to design a reward function?

reinforcement-learning markov-decision-process rewards reward-shaping inverse-rl

modified Aug 4 at 12:10 nbro 18.9k

3

votes

1

answer

36

views

Can AlphaZero considered as Multi-Agent Deep Reinforcement Learning?

deep-learning deep-rl multi-agent-systems alphazero

answered 8 hours ago BlueMoon93 768

0

votes

1

answer

35

views

Mixing CPU and GPU for distributed PyTorch training

pytorch gpu distributed-computing

answered yesterday hal9000 56

0

votes

1

answer

31

views

What ML algorithm should I use that suits this data?

prediction regression linear-regression non-linear-regression

answered 2 days ago Muhammad Rizwan Munawar 1

-1

votes

0

answers

11

views

Decoder.predict not working inside a training model

recurrent-neural-networks long-short-term-memory loss-functions

asked 2 days ago Harshit Sharma 1

1

vote

0

answers

28

views

Why would the loss increase on a single fixed input?

neural-networks loss-functions

modified yesterday nbro 18.9k

0

votes

0

answers

13

views

How to add voice inflections to an existing SV2TTS voice cloning implementation?

deep-learning

asked 2 days ago JustAMartin 101

0

votes

0

answers

16

views

Image classification on SVG format

neural-networks convolutional-neural-networks image-recognition

asked 2 days ago SpiderRico 444

1

vote

0

answers

46

views

How to make sense of label propagation formula in graph neural networks?

deep-learning computer-vision graph-theory graphical-model

modified 2 days ago DuttaA 4,818

-1

votes

0

answers

23

views

Training a Neural Network with Hexadecimal input

neural-networks machine-learning recurrent-neural-networks

asked 2 days ago prashanth balaji 1

-1

votes

0

answers

13

views

How to enable transfer learning for Stylegan2 Tensorflow model training?

machine-learning tensorflow transfer-learning

asked 2 days ago Xie Baoshi 1

1

vote

1

answer

32

views

How to generate labels for self-supervised training?

machine-learning deep-learning datasets supervised-learning self-supervised-learning

modified Aug 4 at 11:52 Vesko Vujovic 131

2

votes

0

answers

55

views

How can I find a specific word in an audio file?

neural-networks machine-learning deep-learning python audio-processing

modified Aug 4 at 12:15 nbro 18.9k

1

vote

0

answers

19

views

Can I use ML to discover via videos the best place to shoot in foosball?

machine-learning video-classification games-of-chance

asked Aug 4 at 15:44 btd 111

2

votes

1

answer

71

views

Why is tic-tac-toe considered a non-deterministic environment?

game-ai environment multi-agent-systems stochastic-policy deterministic-policy

modified Aug 3 at 20:37 nbro 18.9k

2

votes

1

answer

53

views

How to use text as an input for a neural network - regression problem? How many likes/claps an article will get

neural-networks machine-learning deep-learning natural-language-processing recurrent-neural-networks

answered 2 days ago primussucks 86

0

votes

1

answer

30

views

How to input dataset with multi-value properties?

neural-networks training

modified 2 days ago Milan 113

1

vote

0

answers

20

views

When past states contain useful information, does A3C perform better than TD3, given that TD3 does not use an LSTM?

reinforcement-learning comparison long-short-term-memory actor-critic a3c

modified Aug 4 at 11:44 nbro 18.9k

0

votes

0

answers

12

views

Does the selective search algorithm in object detection learn?

convolutional-neural-networks computer-vision search object-detection r-cnn

asked Aug 4 at 17:00 Tibo Geysen 63

1

vote

0

answers

35

views

How to deal with very, very small time-series?

python time-series hidden-markov-model

asked Aug 3 at 19:10 ons bouarada 11

1

vote

3

answers

49

views

How to avoid running out of solutions in genetic algorithm due to selection?

genetic-algorithms genetic-operators

modified Aug 1 at 22:24 nbro 18.9k

0

votes

0

answers

29

views

Why do we use the Target Network for action evaluation in Double deep Q networks

reinforcement-learning deep-learning dqn deep-rl deep-neural-networks

asked Aug 2 at 21:26 CHUKWUDI OGBONNA 1

0

votes

0

answers

18

views

What are some solutions for dealing with time series data that are recorded at uneven intervals?

neural-networks deep-learning recurrent-neural-networks time-series feature-engineering

asked Aug 3 at 8:45 confused 121

1

vote

0

answers

30

views

How can deep Q-learning converge if the targets may not be correct?

reinforcement-learning q-learning dqn deep-rl convergence

modified Aug 2 at 21:03 nbro 18.9k

0

votes

1

answer

57

views

Is it possible to have a fixed trajectory size in the vanilla policy gradient algorithm?

reinforcement-learning policy-gradients pytorch

answered Aug 2 at 13:55 Brale 1,654

0

votes

0

answers

22

views

Is Bayesian NN vs adding random data more accurate?

deep-learning convolutional-neural-networks bayes

asked Aug 3 at 0:45 Samay Lakhani 3

0

votes

0

answers

13

views

Is RCNN resolution-independent, if keeping feature size constant?

convolutional-neural-networks r-cnn

asked Aug 3 at 12:34 Zekko 16

0

votes

0

answers

12

views

Descent Training episodes for LSTM + TD3

reinforcement-learning long-short-term-memory pytorch

asked Aug 3 at 14:20 user2783767 11

1

vote

0

answers

28

views

What does self-play in reinforcement learning lead to?

reinforcement-learning self-play

modified Aug 2 at 20:59 nbro 18.9k

0

votes

0

answers

19

views

TD3+lstm predicting the same output for varying states

reinforcement-learning long-short-term-memory pytorch

modified Aug 3 at 5:58 user2783767 11

Top Questions

Looking for more? Browse the complete list of questions, or popular tags. Help us answer unanswered questions.