Community Profile

photo

Emmanouil Tzorakoleftherakis

MathWorks

Last seen: 13 days ago Active since 2018

Statistics

All
  • 12 Month Streak
  • Personal Best Downloads Level 1
  • Pro
  • Knowledgeable Level 4
  • GitHub Submissions Level 1
  • First Submission
  • Revival Level 2
  • First Answer

View badges

Content Feed

View by

Answered
How to train RL-DQN agent with varying environment?
What you are describing is actually pretty standard process to create robust policies. To change the driving profiles, you can u...

4 months ago | 2

| accepted

Answered
Editing the Q-table before Training in Basic Grid World?
Hello, Please take a look at this link that mentions how you can initialize the table.

4 months ago | 0

| accepted

Answered
Could I learn from past data INCLUDING actions? Could I make vector with actions to be used in a certain order?
Hello, If the historical observations do not depend on the actions taken, (think of stock values, or historical power demand), ...

4 months ago | 0

| accepted

Answered
update reinforcement policy.m weights
Hello, When you want to perform inference on an RL policy, there is no need to consider rewards. The trained policy already kno...

4 months ago | 0

| accepted

Answered
I believe the RL environment template creator has an error in the reset function but I'm not sure
Hello, You are correct the order is wrong. That being said, the order of states depends on your dynamics and how you set up the...

4 months ago | 0

| accepted

Answered
What exactly is Episode Q0? What information is it giving?
Q0 is calculated by performing inference on the critic at the beginning of each episode. Effectively, it is a metric that tells ...

4 months ago | 0

| accepted

Answered
Resume training of a DQN agent. How to avoid Epsilon from being reset to max value?
Hello, This is currently not possible, but it is a great enhancement idea. I have informed the developers about your request an...

4 months ago | 0

| accepted

Answered
Reinforcement learning with Simulink and Simscape
Even outside the thermal domain, you most likely need to start with a simulation model. RL does not need to build that model nec...

4 months ago | 0

Answered
RL training result very different from the result of 'sim'
Please see this post that explains why simulation results may differ during training and after training. If the simulation resu...

4 months ago | 0

| accepted

Answered
RL in dynamic environment
The following example seems relevant, please take a look: https://www.mathworks.com/help/robotics/ug/avoid-obstacles-using-rein...

5 months ago | 0

Answered
MPC Controller giving nice performance during designing but fails on testing
Hello, It sounds to me that the issue is with the linearized model. When you are exporting the controller from MPC Designer, yo...

5 months ago | 0

Answered
What is in a reinforcement learning saved agent .mat file
Why don't you load the file and check? When you saved the agen tin the .mat file, did you save anything else with it? Are you m...

5 months ago | 0

Answered
reinforcement learning PMSM-code
You can find the example here.

5 months ago | 0

| accepted

Answered
How to deal with a large number of state and action spaces?
Even if the NX3 inputs are scalars, I would reorganize them into an "image" and use imageInput layer for the first layer as oppo...

5 months ago | 0

Answered
Q learning algorithm in image processing using matlab.
Hello, Finding an example that exactly matches what you need to do may be challenging. If you are looking for the "deep learnin...

5 months ago | 0

| accepted

Answered
Need help with Model based RL
Hello, If you want to use the existing C code to train with Reinforcement Learning Toolbox, I would use the C caller block to b...

5 months ago | 1

| accepted

Answered
How to set the reinforcement learning block in Simulink to output 9 actions
Hello, the example you are referring to does not output 3 values for the pid gains. The PID gains are "integrated" into the neu...

5 months ago | 0

Answered
Where to update actions in environment?
Reinforcement Learning Toolbox agents expect a static action space, so fixed number of options at each time step. To create a dy...

5 months ago | 0

Answered
How to check the weight and bias which taked by getLearnableParameters?
Can you provide some more details? What does 'wrong answer' mean? How do you know the weights you are seeing are not correct? Ar...

5 months ago | 0

Answered
Gradient in RL DDPG Agent
If you put a break point right before 'gradient' is called in this example, you can step in and see the function implementation....

5 months ago | 0

| accepted

Answered
Soft Actor Critic deploy mean path only
Hello, Please take a look at this option here which was added in R2021a to allow exactly the behavior you mentioned. Hope this...

5 months ago | 0

| accepted

Answered
How to pretrain a stochastic actor network for PPO training?
Hello, Since you already have a dataset, you will have to use Deep Learning Toolbox to get your initial policy. Take a look at ...

5 months ago | 1

Answered
Failure in training of Reinforcement Learning Reinforcement Learning Onramp
Hello, We are aware and working to fix this issue. In the meantime, can you take a look at the following answere? https://www....

6 months ago | 0

Answered
DQN Agent with 512 discrete actions not learning
I would initially revisit the critic architecture for 2 reasons: 1) Network seems a little simple for a 3->512 mapping 2) This...

6 months ago | 0

Answered
How does the Q-Learning update the qTable by using the reinforcement learning toolbox?
Can you try critic.Options.L2RegularizationFactor=0; This parameter is nonzero by default and likely the reason for the discre...

6 months ago | 0

Answered
File size of saved reinforcement learning agents
Hello, Is this parameter set to true? If yes, then it makes sense that mat files are growing in size as the buffer is being pop...

6 months ago | 0

| accepted

Answered
Saving Trained RL Agent after Training
Setting the IsDone flag to 1 does not erase the trained agent - it actually makes sense that the sim was not showing anything be...

6 months ago | 0

| accepted

Answered
How to Train Multiple Reinforcement Learning Agents In Basic Grid World? (Multiple Agents)
Training multiple agents simultaneously is currently only supported in Simulink. The predefined Grid World environments in Reinf...

6 months ago | 0

| accepted

Answered
How to create a neural network for Multiple Agent with discrete and continuous action?
If you want to specify the neural network structures yourself, there is nothing specific you need to do - simply create two acto...

6 months ago | 0

| accepted

Answered
Is it possible apply Reinfocrement Learning to classify data?
If you already have a labeled dataset, supervised learning is the way to go. Reinforcement learning is more for cases where data...

6 months ago | 0

| accepted

Load more