Community Profile

# ryunosuke tazawa

Last seen: 3 Monate vor Aktiv seit 2021

#### Statistics

All

Abzeichen anzeigen

#### Content Feed

Anzeigen nach

Frage

How to get the policy function?
I did simulation with pendulum in Reinforcement learning. After that, I would like to find a policy function of the post -learn...

6 Monate vor | 0 Antworten | 0

### 0

Antworten

Frage

how to applay heatmap for trajectory line?
I want to know how to heatmap line on trajectory(x-y corrdinate)? How can I deal with duplicate data? %% フラクタル次元結果　ヒートマップで描画...

7 Monate vor | 0 Antworten | 0

### 0

Antworten

Frage

How to estimate the fractal dimension of each data point？
I used the Em algorithm to perform point-dimensional estimation and estimated the following parameters. The input is the distan...

7 Monate vor | 0 Antworten | 0

### 0

Antworten

Frage

Reinforcement learning and Paralle computation
I am condcting reinforcement learning with Sac agent. I tried to use GPU and Parallel computation, but in case of using paralle...

8 Monate vor | 0 Antworten | 0

### 0

Antworten

Frage

Suddenly the reward value goes wrong
We are conducting reinforcement learning for two joint controllers. Reinforcement learning method is soft actor critic. The er...

8 Monate vor | 0 Antworten | 0

### 0

Antworten

Frage

How to load pre trained agent model and simulation by using it?
I wanna do simulation by using pre trainned model(agnet). How should I do ? And Is there a way to check if I can use the train...

9 Monate vor | 0 Antworten | 0

### 0

Antworten

Frage

What is Newton's method when there is a lot of input?
I am trying to estimate 3parameters of mixed weibull distribution. And I think the Nweton method for it. But, error happend '...

9 Monate vor | 0 Antworten | 0

### 0

Antworten

Frage

Index exceeds the number of array elements. Index must not exceed 0.
Now I make code which estimate Correlation dimension．But ,error happed 「 Index exceeds the number of array elements. Index mu...

9 Monate vor | 1 Antwort | 0

### 1

Antwort

Frage

How to calculate time delay coordinates？
i want to know the way to calculate the time delay coordinates. I made it . But, if the number of dimensions to be embedded in...

9 Monate vor | 0 Antworten | 0

### 0

Antworten

Frage

How to increase gpu usage?
Now I am doing simulation with reiforcement tool box by using GPU. But, gpu usage can not become high. I checked some points. ...

10 Monate vor | 1 Antwort | 0

### 1

Antwort

Frage

How to make discrete rewards in a continuous state
Is it possible to set a discrete reward in a continuous state? Is it possible to select only one best value from the cumulative...

10 Monate vor | 0 Antworten | 0

### 0

Antworten

Frage

How to compare with the elements before and after
I want know the way to comapre with before element and after element. Please someone tell me. I want to comapare V_Ball(index)...

10 Monate vor | 1 Antwort | 0

### 1

Antwort

Gelöst

Times 2 - START HERE
Try out this test problem first. Given the variable x as your input, multiply it by two and put the result in y. Examples:...

11 Monate vor

Frage

What is the relationship between the number of state values and numerical solutions?
If the number of state values is high, the numerical solution (result) should be good. However, even if the numerical solution ...

etwa ein Jahr vor | 0 Antworten | 0

### 0

Antworten

Frage

What is the episodeQ0?
What does episode Q0 mean? I know it's the output from the critic, but is this a state-valued function? Also, when episode Q0 ...

etwa ein Jahr vor | 0 Antworten | 0

### 0

Antworten

Frage

Is there way to make heatmap with 3variabls?
I have 3 dates and want to make the heatmap with 3datas. z is normalized so that the maximum is 1 and the minimum is 1. Does a...

etwa ein Jahr vor | 1 Antwort | 0

### 1

Antwort

Frage

how to solve low-level graphics?
I want to slove the error about low-level graphics. Could you help me? Theta_Theory = linspace(D2, D1, 10000); Velocity_...

etwa ein Jahr vor | 0 Antworten | 0

### 0

Antworten

Frage

how to make heatmap smooth?
I want to make heatmap smooth, but cell edge can not be without. Please tell me the way . D1 = rad2deg(-4.71); D2 = rad2deg...

etwa ein Jahr vor | 1 Antwort | 0

### 1

Antwort

Frage

How to change the fontsize of labels not axsis.
I want to change the fontsize of labels of x and y. But if I change the font size of the label, the size of the numerical value...

etwa ein Jahr vor | 2 Antworten | 0

### 2

Antworten

Frage

How should I call animation from classdef?
I want to know the way to call the animation from classdef. I defined the animatedline in classdef, and I called the animation ...

etwa ein Jahr vor | 0 Antworten | 0

### 0

Antworten

Frage

How to get the value of value function in soft actor critic?
I want to know the way to get the value of value function. I am using soft actor critic. Someone tell me the way? % Soft...

etwa ein Jahr vor | 0 Antworten | 0

### 0

Antworten

Frage

How to save state in reinforcement learning
I wanna know the way to save information of agent's state in reinforcement learning.

etwa ein Jahr vor | 0 Antworten | 0

### 0

Antworten

Frage

How to reward after one simulation.
I have a simple pendulum throw a ball and perform reinforcement learning so that the error from the target point becomes small. ...

etwa ein Jahr vor | 0 Antworten | 0

### 0

Antworten

Frage

How to add value to matrix?
I want to add elements to matrix. I want to add the calculated value to the end.　In the code below, I would like to add the ca...

etwa ein Jahr vor | 0 Antworten | 0

### 0

Antworten

Frage

How to use isDone frag?
Does isDone frag have the ability to end the episode? I want to do trainning of simplependulum which can move in specific space...

etwa ein Jahr vor | 0 Antworten | 0

### 0

Antworten

Frage

How to stop the simulation in one cycle of Simple Pendulum
I made the code of simple pendulum which is moved by trq. However, depending on the amount of torque, it will continue to rotat...

etwa ein Jahr vor | 0 Antworten | 0

### 0

Antworten

Frage

How can I drow graph of episodes reward?
I made the cord using by reinforcement learning. I can see the graph of Reinforcement learning episode manager but I want to dr...

mehr als ein Jahr vor | 0 Antworten | 0

### 0

Antworten

Frage

How to to updata episodes number?
I am making code by reinforcement learning. The purpose of reinforcement learning describes a simple pendulum that throws a bal...

mehr als ein Jahr vor | 0 Antworten | 0

### 0

Antworten

Frage

How to make it finite?
I want to know the way to fix the erorr. The error masage said that make the value finite. There are four input state variable...

mehr als ein Jahr vor | 0 Antworten | 0

### 0

Antworten

Frage

How should I fix the error 'too many outputs argument'?
I made the cord using by reinforcement learning tool. train_agent Error: reset There are too many output arguments. Error...

mehr als ein Jahr vor | 0 Antworten | 0

Antworten