user avatar
user avatar
user avatar
BlueMoon93
  • Member for 5 years, 2 months
  • Last seen more than a month ago
11 votes
Accepted

How could we build a neural network that is invariant to permutations of the inputs?

5 votes
Accepted

What are other ways of handling invalid actions in scenarios where all rewards are either 0 (best reward) or negative?

4 votes

Is algorithmic bias due to the training dataset used?

3 votes
Accepted

DQN input representation for a card game

3 votes

How to combine backpropagation in neural nets and reinforcement learning?

3 votes

How to constraint the output value of a neural network?

3 votes
Accepted

Can AlphaZero considered as Multi-Agent Deep Reinforcement Learning?

2 votes

In imitation learning, do you simply inject optimal tuples of experience $(s, a, r, s')$ into your experience replay buffer?

2 votes

How should I approach the game "Achtung, Die Kurve" ("Curve Fever") using AI?

2 votes
Accepted

Neural network returns similar output

2 votes

Extracting multiple softmax values from image

2 votes
Accepted

What fast loss convergence indicates on a CNN?

2 votes

What are state-of-the-art ways of using greedy heuristics to initially set the weights of a Deep Q-Network in Reinforcement Learning?

2 votes
Accepted

How many GPUs can these deep learning algorithms be parallelized across (batch parallelization)?

2 votes

Why do non-linear activation functions that produce values larger than 1 or smaller than 0 work?

1 vote

Why does a one-layer hidden network get more robust to poor initialization with growing number of hidden neurons?

1 vote

What model to use for fully unbalanced data?

1 vote

What are the best machine learning models for music composition?

1 vote

How to identify too small network in reinforcement learning?

1 vote

Why does a negative reward for every step really encourage the agent to reach the goal as quickly as possible?