photo

Kaustab Pal


Last seen: 3 days ago |  Active since 2024

Followers: 1   Following: 1

Programming Languages:
MATLAB
Spoken Languages:
English
Pronouns:
He/him

Statistics

  • Knowledgeable Level 1
  • First Answer

View badges

Feeds

View by

Answered
PPO training Stopped Learning.
Hi @Lloyd, The yellow line, Q0, in the plot represents the estimate of the discounted long-term reward at the start of each epi...

3 days ago | 0

Answered
I am Designging a multi-ouput ANN for regression and classification simultaneously but i face error
Hi @Ameer HAmza, To create a Neural Network capable of both classification and regression, you should design the network with t...

4 days ago | 0

Answered
How to Access the Latent Dimension of an Autoencoder
Hi @Eunice Chieng, To retrieve the latent vector from the autoencoder, you can use the encoder network with your input data in ...

4 days ago | 0

Answered
Error when using lstm with cnn
Hi @Mohammed Firas It appears you're facing an issue due to a size mismatch between the output of your final fully connected la...

5 days ago | 0

Answered
How to optimize a bi-exponential signal fitting?
Hi @Susanna Rampichini, It seems there might be an issue with the way you're calculating A1start. I've generated similar data a...

5 days ago | 0

Answered
Edge detection with DIC pattern.
Hi @Tom Lancaster To effectively detect edges in noisy images, it's important to undertake several pre-processing steps before ...

6 days ago | 0

Answered
Optimizing a Regression Learner App for an Electrochemical NO2 Sensor: Dealing with Drift and Input Variations
Hi @Dharmesh Joshi, For the model to work well, it needs to see inputs that are similar to what it saw during training. For exa...

6 days ago | 0

Answered
Quality attributes and metric in training DDPG model
Hello @Ayokunmi Opaniyi, In MATLAB, you can train a reinforcement learning (RL) agent within a specific environment using the ...

6 days ago | 0

Answered
Reasons for bad training performance using prioritized experience replay compared to uniform experience replay using DDPG agent
Hi @Gaurav Prioritized Experience Replay (PER) tends to outperform uniform experience replay in environments where rewards are ...

17 days ago | 1

Answered
How to find the orientation of the entire platform by looking at the overall geometey of the objects/dots?
Hi @shaherbano zaidi, There might be an error in the computation of the pitch and roll angles in your code. The pitch angle is...

18 days ago | 0

Answered
How to normalize the rewards in RL
Hi @Danial Kazemikia, Reward normalization is a crucial step in reinforcement learning (RL) as it stabilizes the training proce...

19 days ago | 0

Answered
Changes in Predicted values after training
Hi @Abiodun Abiola, The output of a neural network (NN) will vary every time you train it. This happens because before trainin...

20 days ago | 0

Answered
Initializing LSTM which is imported using ONNX
Hi @Andreas, It seems you want to determine the input dimension of your imported network. You can easily find this information ...

1 month ago | 0

Answered
How can I isolate some objects from a image?
Hi @Ufuk Can, From what I understand, you need a mask to segment out the balloons. While thresholding is one method to achieve ...

1 month ago | 0

Answered
I don't know why my Monte Carlo Localization simulation doesn't work, I'm using the Monte Carlo Localization toolbox
Hi @Albert Llufriu López, From what I gather, your objective is to use MonteCarloLocalization to estimate your robot's pose. In...

1 month ago | 0

Answered
No effect is observed when I try to use StartVector in eigs to improve numerical efficiency
Hi @Zhao-Yu, Your understanding of using StartVector is correct. The StartVector serves as the initial guess for the iterative ...

1 month ago | 1

Answered
Reinforcement Learning Agent not taking realistic actions
Hi @Karim Darwich, From what I understand, you have a constrained action space, but after training the PPO agent, the agent is ...

1 month ago | 0

| accepted

Answered
Efficiency of "quadprog" in MATLAB
Hi @Trym Gabrielsen, I did a quick analysis between three MATLAB solvers: "mpcActiveSetSolver", "mpcInteriorPointOptions", and ...

1 month ago | 0

Answered
Visualizing Attention for Sequence Data in the Frequency domain
Hi @Luca, To upscale your attention weights from a 256x1 dimension to 512x1, you can utilize the "imresize" function. You c...

2 months ago | 0

Answered
plannerBiRRT seems to extend search tree only in one direction?!
Hi @Fabian Vacha The performance of the plannerBiRRT can be influenced by various parameters. You can try increasing the value...

2 months ago | 0