Skip to main content
Taw's user avatar
Taw's user avatar
Taw's user avatar
Taw
  • Member for 2 years, 11 months
  • Last seen more than a week ago
1 vote

How to setup a reinforcement learning model that changes the values of $x$ to maximize $y$ in $y = f(x)$?

2 votes

Does importance sampling really improve sampling efficiency of TRPO or PPO?

1 vote
Accepted

Is it possible to reverse engineer out the loss based on weights update when data is unknown?

1 vote

Why clip the PPO objective on only one side?

1 vote
Accepted

Are batches useful for REINFORCE without strong episode cutoffs?

0 votes

Are batches useful for REINFORCE without strong episode cutoffs?

1 vote

How do I calculate the gradient of the hinge loss function?

1 vote
Accepted

Is my derivation of the Bellman equation for $q_{\pi}$ in terms of $p(s'|s,a)$ and $r(s,a)$ correct?

1 vote

PPO: multiple discrete actions per step, one depends on the other

2 votes
Accepted

Do I need to normalize all state-space variables? If so, how?

1 vote
Accepted

How to implement PPO without using a Critic

1 vote

Can we Consider Regularization as a "Constraint"?

0 votes

Why does OpenAI's PPO algorithm not follow the discounting method used in Sutton & Barto?

3 votes
Accepted

How should I initialize the weights of the neural network so that the initial policy is uniform?

0 votes
Accepted

What Past Approaches is the "Taylor Swift" Paper Referring To?

0 votes

Triplet Loss- Three forward pass and one backward pass(Propagation)

2 votes
Accepted

In TD(0) with linear function approximation, why is the gradient of $\hat v(S^{\prime}, \mathbf w)$ wrt parameters $\mathbf w$ not considered?

2 votes
Accepted

What is the meaning of the shaded area in the reinforcement learning literature graphs?

3 votes

What specifically is the gradient of the log of the probability in policy gradient methods?

2 votes

Are the authors of the VAE paper writing the PDFs as a function of the random variables?

2 votes

Can I apply reparametrization trick on "any" deep neural network?

8 votes

Why is gradient descent used over the conjugate gradient method?

1 vote

What is the rigorous and formal definition for the direction pointed by a gradient?

1 vote
Accepted

Which is more popular/common way of representing a gradient in AI community: as a row or column vector?

1 vote

Proximal Policy Optimization for continuous control problem

5 votes
Accepted

What is the name of this letter $\mathcal{J}$?

2 votes
Accepted

Why exactly was previously believed that the deterministic policy gradient did not exist?

2 votes
Accepted

What are the roles of the prior $\mathrm{p}(\mathbf{z})$ in a VAE?

1 vote
Accepted

What is the correct notation for an operation that applies to each element of an array independently?

1 vote

How to embed game grid state with walls as an input to neural network