Artificial Intelligence
Profile Activity
Meta user
Network profile
Neil Slater
Summary Answers Questions Tags Badges Bookmarks Bounties Reputation All actions

528 Answers

Votes Activity Newest
36
What's the difference between model-free and model-based reinforcement learning?
Jun 13 '18 at 12:47
36
What is the relation between Q-learning and policy gradients methods?
Apr 28 '18 at 7:47
26
What is the concept of Tensorflow Bottlenecks?
Dec 31 '17 at 9:41
22
How to define states in reinforcement learning?
Aug 31 '18 at 16:02
17
Why does the policy network in AlphaZero work?
Sep 14 '18 at 21:48
16
How does LSTM in deep reinforcement learning differ from experience replay?
Aug 27 '18 at 9:28
15
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?
Mar 22 '18 at 8:24
13
Why should the number of neurons in a hidden layer be a power of 2?
Feb 22 '18 at 18:09
13
What is the difference between an observation and a state in reinforcement learning?
Apr 9 '18 at 21:36
12
How can an AI freely make decisions?
Dec 11 '19 at 0:02
12
How is it that AI can become biased, and what are the proposals to mitigate this?
Feb 17 '19 at 11:28
12
What is the relation between online (or offline) learning and on-policy (or off-policy) algorithms?
Feb 10 '19 at 14:49
11
Is neural networks training done one-by-one?
May 25 '19 at 6:01
10
Why exactly do neural networks require i.i.d. data?
Feb 23 '19 at 20:35
10
Why does DQN require two different networks?
Jul 2 '18 at 9:12
9
What is a “trajectory” in reinforcement learning?
Jul 31 '18 at 15:13
8
Why does the discount rate in the REINFORCE algorithm appear twice?
Aug 22 '18 at 18:58
8
Is the optimal policy always stochastic if the environment is also stochastic?
Feb 15 '19 at 13:47
8
What does “stationary” mean in the context of reinforcement learning?
Aug 21 '18 at 8:36
8
Can the mean squared error be negative?
Nov 17 '18 at 15:56
8
Why are Neural Networks considered Artificially Intelligent?
Oct 22 '18 at 6:10
8
Is Experience Replay like dreaming?
Sep 10 '18 at 6:20
8
Do we know what the units of neural networks will do before we train them?
Jul 5 '18 at 8:02
7
How are the reward functions $R(s)$, $R(s, a)$ and $R(s, a, s')$ equivalent?
Feb 7 '19 at 17:49
7
What is the formula for the momentum and Adam optimisers?
Jan 13 '20 at 9:30
7
Is this idea to calculate the required number of hidden neurons for a single hidden layer neural network correct?
Oct 27 '19 at 20:56
7
Which function $(\hat{y} - y)^2$ or $(y - \hat{y})^2$ should I use to compute the gradient?
May 31 '19 at 15:54
7
Can Q-learning be used for continuous (state or action) spaces?
May 11 '19 at 11:32
7
What is the difference between expected return and value function?
Mar 17 '18 at 21:34
7
Can non-differentiable layer be used in a neural network, if it's not learned?
Aug 24 '18 at 18:58
1
2 3 4 5
…
18

Your privacy

By clicking “Accept all cookies”, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our Cookie Policy.