Skip to main content
GoingMyWay's user avatar
GoingMyWay's user avatar
GoingMyWay's user avatar
GoingMyWay
  • Member for 7 years, 8 months
  • Last seen this week
  • Singapore
20 votes
2 answers
8k views

What is predicted and controlled in reinforcement Learning?

10 votes
3 answers
31k views

What is the loss/cost function of decision trees?

10 votes
2 answers
13k views

How to distinguish episodic task and continuous tasks?

9 votes
3 answers
8k views

How can I understand REINFORCE with baseline is not a actor-critic algorithm?

8 votes
1 answer
7k views

What are soft policies in reinforcement learning?

5 votes
1 answer
11k views

What is the difference between accuracy and precision?

5 votes
1 answer
9k views

What is the relationship between classification and regression in Neural Network?

4 votes
1 answer
4k views

What is the difference between (bias variance) and (underfitting overfitting)?

4 votes
4 answers
2k views

Reinforcement learning, question from Sutton's new book

3 votes
1 answer
1k views

Model stacking, what is the input of meta classifier?

3 votes
1 answer
82 views

Reinforcement learning, how can I get the entropy of an distribution?

3 votes
1 answer
495 views

For any distributions, are mean of the sum of the same distributions equals the sum of the means of the distributions?

3 votes
2 answers
133 views

Multiarmed-bandit problem, why can't we use brute force method to tackle this problem

3 votes
1 answer
1k views

What is the meaning of robustness in machine learning?

3 votes
1 answer
427 views

What does this loss function mean? [duplicate]

3 votes
1 answer
2k views

Adaboost/Boosting, why the base classifier must be weak classifier?

3 votes
1 answer
335 views

Why the $\gamma^t$ is needed here in REINFORCE: Monte-Carlo Policy-Gradient Control (episodic) for $\pi_{*}$?

2 votes
1 answer
180 views

What does IP1 mean in neural networks?

2 votes
1 answer
354 views

Reinforcement Learning, why using data from behaviour policy can be used to optimise the target policy?

2 votes
1 answer
1k views

Calculating Conditional Value at Risk given any distribution

2 votes
1 answer
1k views

Reinforcement Learning, Policy iteration terminal state issue

1 vote
0 answers
142 views

Reinforcement Learning, understanding off-policy methods

1 vote
1 answer
590 views

Reinforcement leaning, what are bounded and ubounded action space mean?

1 vote
1 answer
271 views

N-step DQN question, confused by the termination states

1 vote
1 answer
406 views

Get the new variance of the data [duplicate]

1 vote
1 answer
86 views

Reinforcement learning, is normalizing the reward should also change the learning rate?

1 vote
1 answer
81 views

Predicting an interval by deep learning or other machine learning methods

1 vote
1 answer
289 views

Reinforcement learning, reward in skip frame

1 vote
1 answer
66 views

What is the best way to process categorical variables?

1 vote
2 answers
2k views

Neural Network, questions on DropOut process [duplicate]