Skip to main content
Taw's user avatar
Taw's user avatar
Taw's user avatar
Taw
  • Member for 3 years, 1 month
  • Last seen more than a month ago
9 votes

Why is gradient descent used over the conjugate gradient method?

5 votes
Accepted

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

5 votes
Accepted

If $\gamma \in (0,1)$, what is the on-policy state distribution for episodic tasks?

5 votes

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

3 votes
Accepted

Rescaling time-series data with very spiky pattern for training data in LSTM network

3 votes

What is the optimal score for Tic Tac Toe for a reinforcement learning agent against a random opponent?

3 votes

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

3 votes
Accepted

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

2 votes

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

2 votes
Accepted

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

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

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

2 votes

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

2 votes
Accepted

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

2 votes
Accepted

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

2 votes
Accepted

Reason for relaxing limit in derivative in this context?

2 votes
Accepted

Policy Gradient ( Advantage actor-critic) for multiple simultaneous continuous actions

2 votes
Accepted

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

2 votes
Accepted

Are batches useful for REINFORCE without strong episode cutoffs?

1 vote

Why clip the PPO objective on only one side?

1 vote
Accepted

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

1 vote

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

1 vote

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

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

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

1 vote

How to enforce action bounds between 0 & 1 in soft actor-critic algorithm?

1 vote

Why does critical points and stationary points are used interchangeably?

1 vote

What does it mean "having Lipschitz continuous derivatives"?

1 vote
Accepted

Tensorflow object detection model total loss starts out good, but suddenly explodes up to high loss numbers

1 vote

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