2022 Developer Survey is open! Take survey.
user avatar
user avatar
user avatar
Neil Slater
  • Member for 5 years, 8 months
  • Last seen this week
  • Durham, United Kingdom
43 votes
Accepted

What is the relation between Q-learning and policy gradients methods?

38 votes

What's the difference between model-free and model-based reinforcement learning?

32 votes
Accepted

What are "bottlenecks" in neural networks?

22 votes
Accepted

How to define states in reinforcement learning?

18 votes
Accepted

Why does the policy network in AlphaZero work?

17 votes
Accepted

How does LSTM in deep reinforcement learning differ from experience replay?

17 votes

What is the difference between an observation and a state in reinforcement learning?

17 votes

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

16 votes

How do neural networks play chess?

15 votes

In a CNN, does each new filter have different weights for each input channel, or are the same weights of each filter used across input channels?

14 votes
Accepted

Why should the number of neurons in a hidden layer be a power of 2?

12 votes
Accepted

How can an AI freely make decisions?

12 votes
Accepted

Why does DQN require two different networks?

12 votes
Accepted

How is it that AI can become biased, and what are the proposals to mitigate this?

11 votes

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

11 votes
Accepted

Is neural networks training done one-by-one?

11 votes
Accepted

What is a "trajectory" in reinforcement learning?

10 votes
Accepted

Is LSTM a subcategory of RNN?

9 votes
Accepted

What does "stationary" mean in the context of reinforcement learning?

9 votes
Accepted

Why does the discount rate in the REINFORCE algorithm appear twice?

8 votes
Accepted

What is the formula for the momentum and Adam optimisers?

8 votes
Accepted

Is Experience Replay like dreaming?

8 votes
Accepted

Why are neural networks considered to be artificial intelligence?

8 votes

Can the mean squared error be negative?

8 votes
Accepted

Do we know what the units of neural networks will do before we train them?

8 votes

Can Q-learning be used for continuous (state or action) spaces?

8 votes

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

7 votes
Accepted

Is this idea to calculate the required number of hidden neurons for a single hidden layer neural network correct?

7 votes

Which function $(\hat{y} - y)^2$ or $(y - \hat{y})^2$ should I use to compute the gradient?

7 votes
Accepted

What is the difference between expected return and value function?

1
2 3 4 5
22