Skip to main content
Robby Goetschalckx's user avatar
Robby Goetschalckx's user avatar
Robby Goetschalckx's user avatar
Robby Goetschalckx
  • Member for 3 years, 9 months
  • Last seen more than 1 year ago
  • Eugene, OR, United States
6 votes
Accepted

What's the optimal policy in the rock-paper-scissors game?

6 votes

Why is the target called "target" in Monte Carlo and TD learning if it is not the true target?

4 votes
Accepted

Why do all states appear identical under the function approximation in the Short Corridor task?

3 votes

Why is the perceptron criterion function differentiable?

3 votes

How to perform prediction when some features have missing values?

3 votes
Accepted

How to apply Q-learning when rewards is only available at the last state?

2 votes

How can I process neural network with 25000 input nodes?

2 votes

How are we calculating the average reward ($r(\pi)$) if the policy changes over time?

2 votes

Can we use genetic algorithms to evolve datasets?

2 votes
Accepted

How much can an inclusion of the number of iterations have on the training of an MLP?

1 vote

What is the goal of weight initialization in neural networks?

1 vote

How much overfitting is acceptable?

1 vote

Is this ML task possible?

1 vote

How do weak learners become strong in boosting?

1 vote
Accepted

Q-learning agent stuck at taking same actions

1 vote
Accepted

Mathematical calculation behind decision tree classifier with continuous variables

1 vote

Compressing text using AI by sending only prediction rank of next word

0 votes

How are the "Link Strength true", "Link Strength blind" and "Mutual Information" calculated in this report on Bayesian networks?

0 votes
Accepted

What are the rules behind vector product in gradient?

0 votes

Minimax combined with machine learning to determine if a path should be explored