16Aghnar's user avatar
16Aghnar's user avatar
16Aghnar's user avatar
16Aghnar
  • Member for 5 years, 1 month
  • Last seen more than 1 year ago
6 votes
Accepted

Should I be decaying the learning rate and the exploration rate in the same manner?

3 votes

What kinds of problems can AI solve without using a deep neural network?

4 votes

What kinds of problems can AI solve without using a deep neural network?

3 votes
Accepted

How does the RL agent understand motion if it gets only one image as input?

3 votes
Accepted

How can we teach a neural net to make arbitrary data associations?

1 vote
Accepted

What do the state features of KukaGymEnv represent?

1 vote
Accepted

How is dropout applied to the embedding layer's output?

0 votes

How do I segment each part of a DICOM image?

0 votes
Accepted

Using 3D Points as Inputs to a Neural Net

2 votes
Accepted

Why does the clipped surrogate objective work in Proximal Policy Optimization?

3 votes

Why is the derivative of this objective function 0 if the policy is deterministic?

1 vote

Tuning of PPO metaparameters: a high level overview of what each parameter does