Community Profile

photo

Emmanouil Tzorakoleftherakis


Last seen: Today

MathWorks

49 total contributions since 2018

Emmanouil Tzorakoleftherakis's Badges

  • 6 Month Streak
  • Revival Level 2
  • Knowledgeable Level 2
  • First Answer

View details...

Contributions in
View by

Answered
RL Toolbox: Combine Discrete and Continuous Observations
Does the environments output continuous and discrete observations? If yes, couldn't you use 'rlNumericSpec' for both? The discre...

1 day ago | 0

Answered
RF - Create MATLAB Environment using Custom Functions - myResetFunction
Hi Zhen, I believe you are right - I have informed the documentation team about this.

1 day ago | 0

| accepted

Answered
reinforcement learning using my own function
It looks like your "core" function qualifies as the actual policy (or value function for that matter). The environment would be ...

13 days ago | 0

Answered
How can I find the template for the predefined environment: "CartPole-Discrete"
The predefined environments are coded in an object-oriented way, so you may not find all the info in one file. I would start wit...

13 days ago | 0

Answered
How to continue training a DQN agent in the reinforcement learning toolbox?
Hi James, It looks like the experience buffer is the culprit here. Have a look at this question for a suggestion. Pretty much y...

24 days ago | 0

| accepted

Answered
Measures to improve computation time with reinforcement learning block in Simulink
Hi Enrico, Changing the values of TargetUpdateMethod and TargetUpdateFrequency will not change how often training happens, but ...

24 days ago | 0

Answered
DDPG Control - for non-linear plant control - Q0 does not converge even after 5,000 episodes
Hi Rajesh, Looks to me that this problem has converged. Ideally, the Q0 curve should eventually overlap with the average episod...

24 days ago | 0

Answered
Reinforcement Learning Toolbox: DDPG Agent, Q0 diverging to very high values during training
Hi Johan, It makes sense that stopping the training leads to bad actions since the blown-up critic values probably don't lead t...

4 months ago | 0

Answered
Reinforcement Learning Tool Box : How to change epsilon during training?
Hi Keita, Have a look at this link. The 'EpsilonGreedyExploration' option provides a way to reduce exploration as training prog...

5 months ago | 0

Answered
Reinforcement Learning Toolbox- Multiple Discrete Actions for actor critic agent (imageInputLayer issues)
Hi Anthony, I believe this link should help. Looks like the action space is not set up correctly. For multiple discrete actio...

5 months ago | 0

| accepted

Answered
Create policy evaluation function for RL agent
Can you try defining the size of inputs and outputs in the MATLAB Function block? This seems to be coming up a lot in the error ...

5 months ago | 0

| accepted

Answered
Reinforcement Learning Toolbox - When does algorithm train?
The implementation is based on the algorithm listed here. Weights are being updated at each time step.

5 months ago | 0

| accepted

Answered
RL Toolbox: Proximal Policy Optimisation
Hi Robert, Reinforcement Learning Toolbox in R2019b has a PPO implementation for discrete action spaces. Future releases will i...

5 months ago | 0

Answered
Training an agent of reinforcement learning as a motor's controller, but Matlab doesn't not do training at all?
Hello, It is hard to pinpoint the problem exactly without a repro model, but sounds like training stops prematurely. Can you re...

5 months ago | 0

Answered
DDPG - Noise Model - sample time step - definition
Hi Niklas, This post should be helpful. By "sample time step" the documentation refers to the "step count of the RL trainingpro...

7 months ago | 0

| accepted

Answered
Reinforcement Learning Simulink Block Inital Policy
To use the rl agent block, you need to create an agent first, which also requires a policy architecture. When you set up your ne...

7 months ago | 0

Answered
How to bound DQN critic estimate or RL training progress y-axis
Hello, I believe the best approach here is to figure out why the critic estimate takes large values. Even if you scale the plot...

7 months ago | 0

| accepted

Answered
Reinforcement Learning Simulink Block Inital Policy
If you already have a policy with trained weights, you could just use that directly when creating the agent, instead of creating...

7 months ago | 0

Answered
How to use CarMaker with Reinforcement learning tool box?
Hi Jin, You can use CarMaker with Simulink. After you set up the Simulink model to work with CarMaker, you use the same proces...

7 months ago | 0

Answered
reinforcement learning toolbox - q table
Hi Xinpeng, To see the trained table, you have to do is extract it using ‘getCritic’. Try: critic = getCritic(agent); The v...

7 months ago | 1

| accepted

Answered
Reinforcement Learning Toolbox - Change Action Space
Hi Federico, Unfortunately, the action space is fixed once created. To reduce the amount of times an action is selected, you co...

7 months ago | 1

| accepted

Answered
'sim' command error
Hello, I believe that if you install update 1 (or later) of R2019a release, this issue will be resolved.

7 months ago | 0

Answered
how to create own environment in reinforcement learning
To create a MATLAB environment type rlCreateEnvTemplate('myEnv') This will create a template m file based on the pendulum syst...

7 months ago | 0

Answered
How to show the progress of the training step in an episode?
Hello, You can use 'getLearnableParameterValues' to get the network parameters after training. Can you share some more detail...

8 months ago | 0

Answered
How to visualize episode behaviour with the reinforcement learning toolbox?
Hello, To create a custom MATLAB environment, use the template that pops up after running rlCreateEnvTemplate('myenv') In thi...

9 months ago | 1

| accepted

Answered
Reinforcement Learning - Multiple Discrete Actions
Hi Enrico, Try actionPath = [ imageInputLayer([1 2 1],'Normalization','none','Name','action') fullyConnectedLayer(h...

9 months ago | 0

| accepted

Answered
Reinforcement Learning Toolbox - Intialise Experience Buffer
Hi Enrico, Glad to see that Reinforcement Learning Toolbox is helpful. Regarding your comment about algebraic loops, have you t...

9 months ago | 3

| accepted

Answered
How can I have several actions for a DQN in the Reinforcement Learning Toolbox?
If you type help rlFiniteSetSpec the second example is spec = rlFiniteSetSpec({[0,1];[1,1];[1,2];[1,3]}) If you define all ...

9 months ago | 0

| accepted

Answered
Loading and saving huge matrices in Simulink
On a separate note, it looks like you are implementing Q-learning (?). Q-learning uses tables, which do not scale well when your...

11 months ago | 0

Answered
Design a reinforcement learning (RL) based controller to stabilize a quad copter
Hello, Not sure if you are still looking for a solution, but starting in R2019a, you can do deep reinforcement learning directl...

11 months ago | 0

Load more