nbro
Moderator
  • Member for 5 years, 4 months
  • Last seen this week
3 answers
81 votes
72k views
36 bookmarks
What is self-supervised learning in machine learning?
1 answers
21 votes
8k views
15 bookmarks
What is the Bellman operator in reinforcement learning?
5 answers
20 votes
8k views
7 bookmarks
What is the difference between latent and embedding spaces?
3 answers
18 votes
3k views
8 bookmarks
Why doesn't Q-learning converge when using function approximation?
1 answers
18 votes
14k views
7 bookmarks
What is the credit assignment problem?
3 answers
17 votes
4k views
21 bookmarks
What is geometric deep learning?
4 answers
17 votes
10k views
15 bookmarks
What is non-Euclidean data?
4 answers
14 votes
2k views
12 bookmarks
Which explainable artificial intelligence techniques are there?
3 answers
12 votes
727 views
5 bookmarks
Why teaching only search algorithms in a short introductory AI course?
3 answers
12 votes
2k views
6 bookmarks
Is the optimal policy always stochastic if the environment is also stochastic?
3 answers
11 votes
4k views
5 bookmarks
Why exactly do neural networks require i.i.d. data?
4 answers
11 votes
3k views
2 bookmarks
What are the purposes of autoencoders?
1 answers
10 votes
4k views
11 bookmarks
What is the relation between online (or offline) learning and on-policy (or off-policy) algorithms?
1 answers
6 votes
250 views
1 bookmarks
What is the relation between a policy which is the solution to a MDP and a policy like $\epsilon$-greedy?
1 answers
6 votes
4k views
4 bookmarks
What is the difference between a stationary and a non-stationary policy?
1 answers
6 votes
477 views
Why does a negative reward for every step really encourage the agent to reach the goal as quickly as possible?
1 answers
6 votes
2k views
3 bookmarks
How can the convolution operation be implemented as a matrix multiplication?
1 answers
6 votes
1k views
Which machine learning models are universal function approximators?
1 answers
5 votes
102 views
4 bookmarks
Why should we study causation in artificial intelligence?
3 answers
5 votes
7k views
2 bookmarks
What is the difference between a stochastic and a deterministic policy?
2 answers
5 votes
419 views
1 bookmarks
How are the reward functions $R(s)$, $R(s, a)$ and $R(s, a, s')$ equivalent?
1 answers
5 votes
3k views
1 bookmarks
How can we use linear programming to solve an MDP?
1 answers
4 votes
158 views
What is a generalized MDP?
1 answers
4 votes
886 views
2 bookmarks
What is a graph neural network?
1 answers
4 votes
171 views
1 bookmarks
How are afterstate value functions mathematically defined?
2 answers
4 votes
571 views
Do convolutional neural networks perform convolution or cross-correlation?
1 answers
4 votes
695 views
What are the differences between the DQN variants?
4 answers
4 votes
399 views
2 bookmarks
What other kind of AIs exist apart from goal-driven?
1 answers
3 votes
65 views
How can we convert an MDP to a POMDP?
1 answers
3 votes
241 views
What is teacher forcing?