# Emmanouil Tzorakoleftherakis

### MathWorks

**Content Feed**

已回答

How can i set the constraints on states rather than input and output in mpc?

For linear MPC, you can add constraints on inputs and outputs only. You can either set the desired states to also be outputs (if...

How can i set the constraints on states rather than input and output in mpc?

For linear MPC, you can add constraints on inputs and outputs only. You can either set the desired states to also be outputs (if...

1 day 前 | 0

已回答

How do we know that the PI controller can be modeled using a single neuron?

The network used to model the PI controller is exactly this one actorNet = [ featureInputLayer(numObs) fullyConnected...

How do we know that the PI controller can be modeled using a single neuron?

The network used to model the PI controller is exactly this one actorNet = [ featureInputLayer(numObs) fullyConnected...

3 days 前 | 0

已回答

Using a Simulink dynamic motorcycle in a driving scenario trajectory.

Here is a video that shows how to do that using Model Predictive Control Toolbox: https://www.mathworks.com/videos/understandin...

Using a Simulink dynamic motorcycle in a driving scenario trajectory.

Here is a video that shows how to do that using Model Predictive Control Toolbox: https://www.mathworks.com/videos/understandin...

5 days 前 | 0

已回答

question about external action of DDPG

The loss function does not change. What happens is that the experience buffer is populated with the action from the external sig...

question about external action of DDPG

The loss function does not change. What happens is that the experience buffer is populated with the action from the external sig...

5 days 前 | 0

| 已接受

已回答

use a linear state space model in NLMPC

Is there a reason you want to convert to nonlinear MPC? If you get a good solution with linear MPC, going to nonlinear will only...

use a linear state space model in NLMPC

Is there a reason you want to convert to nonlinear MPC? If you get a good solution with linear MPC, going to nonlinear will only...

6 days 前 | 0

已回答

Integral MPC in Simulink

Why don't you use the MVRate constraint instead of adding the term in the cost function? https://www.mathworks.com/help/mpc/ug...

Integral MPC in Simulink

Why don't you use the MVRate constraint instead of adding the term in the cost function? https://www.mathworks.com/help/mpc/ug...

6 days 前 | 0

已回答

Why reinforcement learning has different results of action between sim() and getAction()?

Hi, Which release are you using? We tried in R2023a and R2023b with UseExplorationPolicy =0 and getAction and sim provide the s...

Why reinforcement learning has different results of action between sim() and getAction()?

Hi, Which release are you using? We tried in R2023a and R2023b with UseExplorationPolicy =0 and getAction and sim provide the s...

6 days 前 | 0

已回答

Epsilon greedy policy for DQN

You can use the formula here to calculate the epsilon value

Epsilon greedy policy for DQN

You can use the formula here to calculate the epsilon value

6 days 前 | 1

| 已接受

已回答

Reinforcement learning agent for mixed action space.

Reinforcement Learning Toolbox does not support agents with both continuous and discrete actions. Can you share some more detail...

Reinforcement learning agent for mixed action space.

Reinforcement Learning Toolbox does not support agents with both continuous and discrete actions. Can you share some more detail...

6 days 前 | 0

已回答

can i decide the RL agents actions

It seems like the paper you saw uses some logic to implement the behavior you mention. You could do the same with an if statemen...

can i decide the RL agents actions

It seems like the paper you saw uses some logic to implement the behavior you mention. You could do the same with an if statemen...

6 days 前 | 0

已回答

The agent can learn the policy through the external action port in the RL Agent so that the agent mimics the output of the reference signal

It seems the agent started learning how to imitate the existing controller but needs more time. What does the Episode Manager lo...

The agent can learn the policy through the external action port in the RL Agent so that the agent mimics the output of the reference signal

It seems the agent started learning how to imitate the existing controller but needs more time. What does the Episode Manager lo...

6 days 前 | 0

已回答

How to import a model built by comsol in the reinforcement learning designer

I haven't used Comson before but it seems that you may be able to co-simulate your model with Simulink. In that case, the proces...

How to import a model built by comsol in the reinforcement learning designer

I haven't used Comson before but it seems that you may be able to co-simulate your model with Simulink. In that case, the proces...

6 days 前 | 0

已回答

Multi-Agent Reinforcement learning

As of R2023b, you can do multi-agent reinforcement learning using MATLAB environments. Please take a look at this example and R2...

Multi-Agent Reinforcement learning

As of R2023b, you can do multi-agent reinforcement learning using MATLAB environments. Please take a look at this example and R2...

2 months 前 | 0

已回答

How can i scale the action of DDPG agent in Reinforcement Learning?

DDPG training works by adding noise on top of the actor output to promote exploration. In that case you may see constraint viola...

How can i scale the action of DDPG agent in Reinforcement Learning?

DDPG training works by adding noise on top of the actor output to promote exploration. In that case you may see constraint viola...

2 months 前 | 0

已回答

How I can define eight discrete actions in RL section

The implementation shown here is one option. Hope that helps

How I can define eight discrete actions in RL section

The implementation shown here is one option. Hope that helps

2 months 前 | 0

已回答

In SImulink, during DDPG training to regulate the CO2 concentration the environment is not simulating. I can see only the variables specified in function is updating.

Hello, I would start by taking a look at the output of the agent. If the agent output does not make sense, the environment will...

In SImulink, during DDPG training to regulate the CO2 concentration the environment is not simulating. I can see only the variables specified in function is updating.

Hello, I would start by taking a look at the output of the agent. If the agent output does not make sense, the environment will...

3 months 前 | 0

已回答

5G Handover with Reinforcement Learning, mismatch of input channels and observations in reinforcement learning representation

I suspect you did not set up your critic network properly. If you share that code snippet we can take a closer look. An alternat...

5G Handover with Reinforcement Learning, mismatch of input channels and observations in reinforcement learning representation

I suspect you did not set up your critic network properly. If you share that code snippet we can take a closer look. An alternat...

3 months 前 | 0

已回答

Implementing mpctools package (from Rawlings group) in Simulink

I cannot comments on mpctools, but if your objective is to use IPOPT in Simulink, Model Predictive Control Toolbox allows you to...

Implementing mpctools package (from Rawlings group) in Simulink

I cannot comments on mpctools, but if your objective is to use IPOPT in Simulink, Model Predictive Control Toolbox allows you to...

3 months 前 | 0

已回答

I want to print out multiple actions in reinforcement learning

Hi, If you want to create an agent that outputs multiple actions, you need to make sure the actor network is set up accordingly...

I want to print out multiple actions in reinforcement learning

Hi, If you want to create an agent that outputs multiple actions, you need to make sure the actor network is set up accordingly...

3 months 前 | 0

已回答

Issue with Q0 Convergence during Training using PPO Agent

It seems you set the training to stop when the episode reward reaches the value of 0.985*(Tf/Ts)*3. I cannot comment on the valu...

Issue with Q0 Convergence during Training using PPO Agent

It seems you set the training to stop when the episode reward reaches the value of 0.985*(Tf/Ts)*3. I cannot comment on the valu...

3 months 前 | 1

| 已接受

已回答

Where is the actual storage location of the RL agent's weights.

Hello, You can implement the trained policy with automatic code generation, e.g. with MATLAB Coder, Simulink Coder and so on. Y...

Where is the actual storage location of the RL agent's weights.

Hello, You can implement the trained policy with automatic code generation, e.g. with MATLAB Coder, Simulink Coder and so on. Y...

3 months 前 | 0

已回答

How do I find the objective/cost function for the example Valet parking using multistage NLMPC. (https://www.mathworks.com/help/mpc/ug/parking-valet-using-nonlinear-model-pred

Hi, The example you mentioned used MPC on two occasions: 1) On the outer loop for planning through the Vehicle Path Plannerblo...

How do I find the objective/cost function for the example Valet parking using multistage NLMPC. (https://www.mathworks.com/help/mpc/ug/parking-valet-using-nonlinear-model-pred

Hi, The example you mentioned used MPC on two occasions: 1) On the outer loop for planning through the Vehicle Path Plannerblo...

3 months 前 | 0

已回答

Replace RL type (PPO with DPPG) in a Matlab example

PPO is a stochastic agent whereas DDPG is deterministic. This means that you cannot just use actors and critics designed for PPO...

Replace RL type (PPO with DPPG) in a Matlab example

PPO is a stochastic agent whereas DDPG is deterministic. This means that you cannot just use actors and critics designed for PPO...

3 months 前 | 1

| 已接受

已回答

NMPC Controller not buildable for Raspberry Pi

Hard to tell without providing more details but I have a suspicion that you are defining the state and const functions as anonym...

NMPC Controller not buildable for Raspberry Pi

Hard to tell without providing more details but I have a suspicion that you are defining the state and const functions as anonym...

3 months 前 | 0

已回答

Regarding Default Terms in DNN

Which algorithm are you using? You can log loss data by following the guidelines here.

Regarding Default Terms in DNN

Which algorithm are you using? You can log loss data by following the guidelines here.

4 months 前 | 1

已回答

How to start, pause, log information, and continue a simscape simulation?

If you go for #2, why don't you set it so that you have episodes that are 10 seconds long? When each episode ends, change the i...

How to start, pause, log information, and continue a simscape simulation?

If you go for #2, why don't you set it so that you have episodes that are 10 seconds long? When each episode ends, change the i...

4 months 前 | 0

已回答

how to put some obstacles into my envrionment then to train my agent to avoid the obstacles and find a optimal path to follow using reiforment learning by simulink?

This example may be helpful.

how to put some obstacles into my envrionment then to train my agent to avoid the obstacles and find a optimal path to follow using reiforment learning by simulink?

This example may be helpful.

4 months 前 | 0

已回答

how to get the cost function result from model predictive controller?

Please take a look at the doc page of mpcmove. The Info output containts a field called Cost. You can use it to visualize how th...

how to get the cost function result from model predictive controller?

Please take a look at the doc page of mpcmove. The Info output containts a field called Cost. You can use it to visualize how th...

4 months 前 | 0

已回答

The solution obtained with the nlmpcmove function of the mpc toolbox is not "reproducible"?

Hi, For problem 1: I am not sure what's inside that state function but presumably there is some integrator that gives you k+1....

The solution obtained with the nlmpcmove function of the mpc toolbox is not "reproducible"?

Hi, For problem 1: I am not sure what's inside that state function but presumably there is some integrator that gives you k+1....

4 months 前 | 0

已回答

How to keep actions values at minimum before disturbance and let the agent choose different action values only after the disturbance?

Please take a look here. As of R2022a you can place the RL policy block inside a triggered subsystem and only enable the subsyst...

How to keep actions values at minimum before disturbance and let the agent choose different action values only after the disturbance?

Please take a look here. As of R2022a you can place the RL policy block inside a triggered subsystem and only enable the subsyst...

4 months 前 | 0