Philip Raeisghasem's user avatar
Philip Raeisghasem's user avatar
Philip Raeisghasem's user avatar
Philip Raeisghasem
  • Member for 4 years, 11 months
  • Last seen more than 3 years ago
31 votes
Accepted

What is the Bellman operator in reinforcement learning?

10 votes
Accepted

What loss function to use when labels are probabilities?

7 votes
Accepted

How is the policy gradient calculated in REINFORCE?

7 votes
Accepted

How can the $\lambda$-return be defined recursively?

6 votes

Which kind of prioritized experience replay should I use?

6 votes
Accepted

Are there reinforcement learning algorithms that scale to large problems?

6 votes
Accepted

Why isn't the ElliotSig activation function widely used?

5 votes

What would be a good comprehensive source about the different forms of classical learning in mammals?

5 votes
Accepted

What determines the values of weights in a neural network?

5 votes
Accepted

Apart from the state and state-action value functions, what are other examples of value functions used in RL?

4 votes

Which fields of AI are actively researching consciousness?

4 votes

Can a neuron have both a bias and a threshold?

4 votes
Accepted

What is the meaning of the statement $\forall x \exists y \forall z (z \neq y \iff f(x) \neq z)$?

4 votes
Accepted

Why don't we decorrelate transitions for policy-based data?

3 votes
Accepted

What is the motivation behind using a deterministic policy?

3 votes

Can (trained) neural networks be combined with symbolic AI to perform operations like AND?

3 votes

Is there any grid world dataset or generator for reinforcement learning?

2 votes
Accepted

Is there a way to train an RL agent without any environment?

2 votes

Why is $M_t$ (the emphasis) helping in correcting for the state distribution in the Emphatic TD algorithm?

2 votes

Can neural networks learn to ignore an input datum?

2 votes
Accepted

Can I export a trained machine learning model so that others case use it?

2 votes
Accepted

Does backpropagation update weights one layer at a time?

2 votes
Accepted

Understanding the n-step off-policy SARSA update

2 votes
Accepted

How can alpha zero learn if the tree search stops and restarts before finishing a game?

2 votes

What is the input to AlphaGo's neural network?

2 votes

Reinforcement learning with uniformly random dynamics

1 vote
Accepted

How should I implement the backward pass through a flatten layer of a CNN?

1 vote

How do I compute the variance of the return of an evaluation policy using two behaviour policies?

1 vote

Skip-Gram Model Training

1 vote

What do the vectors of the center and outside word look like in word2vec?