Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.

Sign up to join this community

Anybody can ask a question

Anybody can answer

The best answers are voted up and rise to the top

Explore our Questions

Ask Question

more tags

Active Hot Week Month

0

votes

0

answers

3

views

Policy Improvement Theorem for epsilon-greedy policy

reinforcement-learning monte-carlo greedy-ai policy-improvement

asked 6 mins ago Nishanth Rao 33

0

votes

1

answer

12

views

how to switch Q target and Q network in deep Q learning

deep-learning q-learning deep-rl

modified 17 mins ago user5093249 325

0

votes

0

answers

27

views

Using a model-based method to build an accurate day trading environment model

reinforcement-learning policy-gradients model-based

modified 36 mins ago jgauth 101

3

votes

1

answer

94

views

Why is update rule of the value function different in policy evaluation and policy iteration?

reinforcement-learning comparison policy-iteration policy-evaluation dynamic-programming

modified 46 mins ago Nishanth Rao 33

1

vote

1

answer

11

views

Is there any good source for when the pole actually starts all the way at the bottom, in the cartpole problem?

reinforcement-learning reference-request

answered 53 mins ago Neil Slater 12.6k

0

votes

1

answer

79

views

Handle non-existing states in q-learning

reinforcement-learning q-learning dqn deep-rl

modified 5 hours ago PetrH 121

3

votes

2

answers

50

views

How to represent and work with the feature matrix for graph convolutional network (GCN) if the number of features for each node is different?

machine-learning deep-learning convolutional-neural-networks geometric-deep-learning

answered 14 hours ago brazofuerte 403

1

vote

1

answer

41

views

What does the Fourier transformed image mean?

computer-vision image-processing

modified 14 hours ago Community♦ 1

0

votes

0

answers

15

views

Can you find another reason for sample inefficiency of model-free on-policy Deep Reinforcement Learning?

deep-learning reinforcement-learning deep-rl sample-efficiency sample-complexity

asked 16 hours ago Ray Walker 161

2

votes

2

answers

82

views

Are there neural networks that accept graphs or trees as inputs?

neural-networks recurrent-neural-networks geometric-deep-learning graphs graph-neural-networks

modified 17 hours ago brazofuerte 403

40

votes

6

answers

2k

views

What is fuzzy logic?

deep-network terminology fuzzy-logic

modified 19 hours ago peterh - Reinstate Monica 201

38

votes

8

answers

32k

views

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?

deep-learning convolutional-neural-networks image-recognition

modified 19 hours ago peterh - Reinstate Monica 201

32

votes

6

answers

9k

views

Why do CNN's sometimes make highly confident mistakes, and how can one combat this problem?

convolutional-neural-networks python tensorflow keras bayesian-deep-learning

modified 19 hours ago peterh - Reinstate Monica 201

4

votes

2

answers

38

views

What is the proof that the branch and bound algorithm always finds optimal path in a graph?

search proofs graphs branch-and-bound

modified 20 hours ago nbro♦ 17.1k

Browse more Questions

Artificial Intelligence Stack Exchange works best with JavaScript enabled