回答済み
Question about using the nonlinear model predictive control toolbox
nlmpcmove function uses fmincon from Optimization Toolbox. Pleaase take a look at this doc page for more details

3年以上前 | 0

回答済み
Adaptive MPC for LPV systems
This is possible with Model Predictive Control Toolbox yes, please take a look at this example.

3年以上前 | 0

回答済み
Is it possible to pass simulink NMPC parameters as struct?
Please take a look at my answer here

3年以上前 | 0

| 採用済み

回答済み
Get nonlinear model from Simulink to Matlab
Hi Daniel, Unfortunately Model Predictive Control Toolbox does not currently support using a Simulink model directly as a predi...

3年以上前 | 0

| 採用済み

回答済み
Binary Manipulated Variable in NLMPC
Unfortunately Model Predictive Control Toolbox does not currently support mixed-integer problems for NLMPC.

3年以上前 | 0

回答済み
Import Timeseries on Simulink as raw structure and not as single data samples at certain simulation time
It seems to me that you want to implement the MPC preview capability in Simulink. This example actually has a custom previewer b...

3年以上前 | 0

回答済み
NLMPC state function parameters
Hi, Given that it is not possible to package all variables into a struct and feed them into the MPC controller that way (it's n...

3年以上前 | 0

| 採用済み

回答済み
Can I Generate C Code for TD3 or DDPG agent？
Yes. Here is an example

3年以上前 | 0

回答済み
Applying reinforcement learning with two continuous actions. During training one varies but the other is virtually static.
You should be able to use a single agent for this task. Since you are using DDPG, the first thing I would check is whether the n...

3年以上前 | 0

回答済み
How the generated parameters of agent are related PI/PID controller in reinforcement learning algorithm
This example uses an actor network that works as a PI controller. This is possible because we are using a customer layer called ...

3年以上前 | 0

| 採用済み

回答済み
Constantly high negative reward in RL agent
You need to see what the actions generated by the RL Agent block are and how they affect the quadrotor dynamics. That's what it ...

3年以上前 | 0

| 採用済み

回答済み
Load PPO agent and check layer
The neural network architectures are not immediately available from the agent object. You can extract and inspect layers using g...

3年以上前 | 0

回答済み
cumulative reward in RL AGENT block.
It's not very clear what you are asking, but the cumulative reward changes during each episode. It also depends on the sample ti...

3年以上前 | 0

回答済み
Sending episode number to simulink during training
The training stats are not available until after training is done, so you cannot use trainingStats.EpisodeIndex during training....

3年以上前 | 0

| 採用済み

回答済み
How to modify actions in experiences during a reinforcement learning training
If you are working in Simulink, you can use the "Last Action" port in the RL Agent block to indicate what was the action that wa...

4年弱前 | 1

回答済み
How to get the actor network of a trained policy gradient agent?
Hello, To get the neural network model you can use net = getModel(getActor(agent)) To get learnable parameters you can use g...

4年弱前 | 0

| 採用済み

回答済み
How to see actions when using the train() function in RL tool box.
Hello, To log action data throughout an episode, you would need to do so from inside the step function of your environment. You...

4年弱前 | 1

| 採用済み

回答済み
Training Quadrotor using PPO agent
Hello, There are multiple things not set up properly, including: 1) The isdone flag seems to be 1 all the time leading to epis...

約4年前 | 0

回答済み
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...

5年弱前 | 2

| 採用済み

回答済み
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.

5年弱前 | 0

| 採用済み

回答済み
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), ...

5年弱前 | 1

| 採用済み

回答済み
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...

5年弱前 | 0

| 採用済み

回答済み
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...

5年弱前 | 0

| 採用済み

回答済み
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 ...

5年弱前 | 2

| 採用済み

回答済み
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...

5年弱前 | 0

| 採用済み

回答済み
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...

5年弱前 | 0

回答済み
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...

5年弱前 | 0

| 採用済み

回答済み
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年弱前 | 0

| 採用済み

回答済み
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年弱前 | 0

回答済み
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年弱前 | 0