Skip to main content
Share Your Experience: Take the 2024 Developer Survey
Neil Slater's user avatar
Neil Slater's user avatar
Neil Slater's user avatar
Neil Slater
  • Member for 7 years, 9 months
  • Last seen this week
  • Durham, United Kingdom
53 votes

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

53 votes
Accepted

How is ChatGPT aware of today's date?

47 votes
Accepted

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

44 votes
Accepted

Why do ChatGPT “jailbreaks” work?

39 votes
Accepted

What are "bottlenecks" in neural networks?

37 votes
Accepted

Is the "Chinese room" an explanation of how ChatGPT works?

25 votes
Accepted

Why do many AI bots feel the need to be know-it-alls?

24 votes
Accepted

How to define states in reinforcement learning?

21 votes
Accepted

Why does the policy network in AlphaZero work?

21 votes

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

20 votes

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

20 votes

How do neural networks play chess?

17 votes
Accepted

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

16 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?

13 votes
Accepted

Why does DQN require two different networks?

13 votes
Accepted

What is a "trajectory" in reinforcement learning?

13 votes
Accepted

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

12 votes

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

12 votes
Accepted

How can an AI freely make decisions?

11 votes
Accepted

Is neural networks training done one-by-one?

11 votes

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

11 votes

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

10 votes
Accepted

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

10 votes

Can the mean squared error be negative?

10 votes
Accepted

Is LSTM a subcategory of RNN?

10 votes

How is ChatGPT able to repeat random numbers?

9 votes
Accepted

When to use the state value function $V(s)$ and when to use the state-action value function $Q(s, a)$?

9 votes
Accepted

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

9 votes
Accepted

What is the formula for the momentum and Adam optimisers?

1
2 3 4 5
28