user avatar
user avatar
user avatar
devidduma
  • Member for 2 years, 3 months
  • Last seen this week
5 votes

Deep Q-Learning "catastrophic drop" reasons?

3 votes

What are the best hyper-parameters to tune in reinforcement learning?

3 votes
Accepted

Should I allow NN to infer relationships of inputs?

2 votes

Which introductory courses (preferably video lectures) could I use to learn ML for applying ML to black hole simulations?

2 votes
Accepted

Can AI be used for grading code copy exercises and adjust difficulty based on these scores?

2 votes
Accepted

Where can I find authentic references on "categorical cross entropy" and "categorical accuracy metric"?

1 vote
Accepted

Why does my actor-critic network always give either -1 or 1 at the output layer?

1 vote
Accepted

Number of classes vs number of parameters/layers?

1 vote

Proximal Policy Optimization for continuous control problem