user avatar
user avatar
user avatar
nbro
  • Member for 5 years, 9 months
  • Last seen this week
85 votes
3 answers
77k views

What is self-supervised learning in machine learning?

23 votes
1 answer
10k views

What is the Bellman operator in reinforcement learning?

23 votes
5 answers
10k views

What is the difference between latent and embedding spaces?

21 votes
5 answers
13k views

What is non-Euclidean data?

20 votes
1 answer
17k views

What is the credit assignment problem?

19 votes
3 answers
3k views

Why doesn't Q-learning converge when using function approximation?

17 votes
3 answers
4k views

What is geometric deep learning?

15 votes
3 answers
2k views

Which explainable artificial intelligence techniques are there?

13 votes
3 answers
5k views

Why exactly do neural networks require i.i.d. data?

13 votes
3 answers
782 views

Why teaching only search algorithms in a short introductory AI course?

12 votes
3 answers
3k views

Is the optimal policy always stochastic if the environment is also stochastic?

12 votes
4 answers
3k views

What are the purposes of autoencoders?

11 votes
1 answer
4k views

What is the relation between online (or offline) learning and on-policy (or off-policy) algorithms?

8 votes
3 answers
9k views

What is the difference between a stochastic and a deterministic policy?

7 votes
1 answer
5k views

What is the difference between a stationary and a non-stationary policy?

6 votes
1 answer
605 views

Why does a negative reward for every step really encourage the agent to reach the goal as quickly as possible?

6 votes
1 answer
2k views

Which machine learning models are universal function approximators?

6 votes
1 answer
320 views

What is the relation between a policy which is the solution to a MDP and a policy like $\epsilon$-greedy?

6 votes
1 answer
4k views

How can the convolution operation be implemented as a matrix multiplication?

5 votes
2 answers
637 views

How are the reward functions $R(s)$, $R(s, a)$ and $R(s, a, s')$ equivalent?

5 votes
1 answer
1k views

What is a graph neural network?

5 votes
1 answer
4k views

How can we use linear programming to solve an MDP?

5 votes
1 answer
106 views

Why should we study causation in artificial intelligence?

4 votes
1 answer
168 views

What is a generalized MDP?

4 votes
4 answers
411 views

What other kind of AIs exist apart from goal-driven?

4 votes
1 answer
349 views

Is there any difference between a control and an action in reinforcement learning?

4 votes
2 answers
778 views

Do convolutional neural networks perform convolution or cross-correlation?

4 votes
1 answer
191 views

How are afterstate value functions mathematically defined?

4 votes
1 answer
211 views

Why do we have two similar action selection strategies for UCB1?

3 votes
1 answer
103 views

What are knowledge graph embeddings?