Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.

Sign up to join this community

Anybody can ask a question

Anybody can answer

The best answers are voted up and rise to the top

Explore our Questions

Ask Question

more tags

Active Hot Week Month

1

vote

1

answer

16

views

Is there a multi-agent deep reinforcement learning algorithm which is for environments with only discrete action spaces (Not hybrid)?

reinforcement-learning deep-rl discrete-action-spaces multi-agent-rl

answered 23 mins ago Felipe Costa 83

0

votes

0

answers

3

views

Why was the VC dimension not defined for all configurations of $d$ points?

reference-request computational-learning-theory history vc-dimension

asked 51 mins ago nbro♦ 26.9k

0

votes

0

answers

4

views

Can someone please explain to me the Glove Algorithm [Machine Learning]

natural-language-processing word2vec

asked 1 hour ago SWARALIPI BOSE 1

2

votes

1

answer

112

views

How can I reduce combinatorial explosion in an MCTS-like algorithm for program induction?

monte-carlo-tree-search combinatorics inductive-programming program-synthesis

modified 2 hours ago Community♦ 1

4

votes

3

answers

109

views

What are the typical sizes of practical/commercial artificial neural networks?

neural-networks machine-learning reference-request autonomous-vehicles

answered 3 hours ago papiot 1

0

votes

0

answers

6

views

Does batch normalization affects the possible solution distribution?

batch-normalization

asked 3 hours ago Fred Guth 136

0

votes

0

answers

4

views

Atari Gym Amidar is only starting after a certain number of episodes

reinforcement-learning open-ai gym atari-games

asked 3 hours ago Lennart 1

1

vote

0

answers

9

views

Are policy gradient methods good for large discrete action spaces?

reinforcement-learning dqn policy-gradients

asked 3 hours ago user9317212 103

0

votes

2

answers

32

views

Unet Overfitting for binary segmentation of fake images

deep-learning computer-vision tensorflow image-segmentation u-net

answered 4 hours ago bguetarni 11

0

votes

2

answers

40

views

What is the process working on Tensorflow model.fit()?

machine-learning tensorflow training datasets

answered 4 hours ago bguetarni 11

3

votes

1

answer

96

views

What's the difference between estimation and approximation error?

machine-learning computational-learning-theory bias-variance-tradeoff approximation-error estimation-error

modified 6 hours ago nbro♦ 26.9k

2

votes

2

answers

93

views

Why is the equation $\mathbb{E} \left[ (Y - \hat{Y})^2 \right] = \left(f(X) - \hat{f}(X) \right)^2 + \operatorname{Var} (\epsilon)$ true?

machine-learning proofs function-approximation statistical-ai probability-theory

modified 7 hours ago nbro♦ 26.9k

1

vote

1

answer

82

views

Developing character tactics via repeated trials

game-ai problem-solving

modified 10 hours ago Community♦ 1

3

votes

1

answer

1k

views

Why does the adversarial search minimax algorithm use Depth-First Search (DFS) instead of Breadth-First Search (BFS)?

search minimax breadth-first-search depth-first-search adversarial-search

modified 17 hours ago nbro♦ 26.9k

Browse more Questions

Artificial Intelligence Stack Exchange works best with JavaScript enabled