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 1 Bountied Hot Week Month

1

vote

0

answers

3

views

How should I define the reward function for the Connect Four game?

reinforcement-learning ai-design markov-decision-process rewards

modified 46 secs ago nbro♦ 13.9k

1

vote

0

answers

6

views

Is the TD-residual defined for timesteps $t$ past the length of the episode?

reinforcement-learning policy-gradients temporal-difference

modified 7 mins ago bxw 33

1

vote

0

answers

5

views

Why can the core reinforcement learning algorithms be applied to POMDPs?

reinforcement-learning markov-decision-process pomdp

modified 35 mins ago nbro♦ 13.9k

2

votes

2

answers

11

views

Why is there an expectation sign in the Bellman equation?

reinforcement-learning value-function expectation bellman-equations

modified 46 mins ago nbro♦ 13.9k

6

votes

1

answer

170

views

Why do Bellman equations indirectly create a policy?

reinforcement-learning comparison policy-gradients bellman-equations

modified 1 hour ago nbro♦ 13.9k

9

votes

1

answer

2k

views

What is the Bellman operator in reinforcement learning?

reinforcement-learning terminology math

modified 1 hour ago nbro♦ 13.9k

2

votes

1

answer

90

views

Why is this ResNet50 misclassifying objects?

machine-learning deep-learning classification image-recognition keras

modified 1 hour ago Community♦ 1

1

vote

1

answer

22

views

Which humanoid robots have open-source software (or hardware)?

reference-request robotics resource-request robots humanoid-robots

modified 2 hours ago tynowell 131

2

votes

0

answers

31

views

Does Rice's theorem prove safe AI is undecidable?

agi proofs ai-safety theory-of-computation

modified 2 hours ago nbro♦ 13.9k

1

vote

0

answers

11

views

How can I find the appropriate reward value for my reinforcement learning problem?

reinforcement-learning ai-design rewards

modified 2 hours ago nbro♦ 13.9k

1

vote

1

answer

16

views

What is the role of convex optimisation in AI systems?

machine-learning optimization

modified 5 hours ago nbro♦ 13.9k

1

vote

1

answer

20

views

Should I always start from the same start state in reinforcement learning?

reinforcement-learning training gym

answered 5 hours ago Edoardo Guerriero 336

0

votes

2

answers

20

views

How can I train a neural network if I don't have enough data?

neural-networks backpropagation optimization matlab

answered 5 hours ago Paul Higazi 46

7

votes

3

answers

382

views

What types of applications qualify as “compound intelligences”?

machine-learning definitions applications reference-request swarm-intelligence

modified 5 hours ago nbro♦ 13.9k

Browse more Questions

Artificial Intelligence Stack Exchange works best with JavaScript enabled