Tjyylli

How to create a command for the "strange m" symbol in latex?

What is the definining line between a helicopter and a drone a person can ride in?

What's the difference between using dependency injection with a container and using a service locator?

Meaning of this sentence, confused by まで

If gravity precedes the formation of a solar system, where did the mass come from that caused the gravity?

Suing a Police Officer Instead of the Police Department

Why did Bronn offer to be Tyrion Lannister's champion in trial by combat?

How to keep bees out of canned beverages?

Is Bran literally the world's memory?

tabularx column has extra padding at right?

Who can become a wight?

2 sample t test for sample sizes - 30,000 and 150,000

How to produce a PS1 prompt in bash or ksh93 similar to tcsh

Is "ein Herz wie das meine" an antiquated or colloquial use of the possesive pronoun?

Construct a nonabelian group of order 44

Why did Israel vote against lifting the American embargo on Cuba?

Assertions In A Mock Callout Test

Why doesn't the university give past final exams' answers?

How to break 信じようとしていただけかも知れない into separate parts?

Married in secret, can marital status in passport be changed at a later date?

lm and glm function in R

What could prevent concentrated local exploration?

Sorting the characters in a utf-16 string in java

Providing direct feedback to a product salesperson

OpenAI Gym custom env. multi discrete action space or tuple space example?

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty{ height:90px;width:728px;box-sizing:border-box;
}

0

I am trying to implement my custom env. into the openai gym

So far, I am using continuous action space (6 ch)

so input dimension can be used with env.action_space.shape[0]

But I found that it is not stable in my env. I decided to move to multi discrete space like with limited interger values (100, 100, 10, 5, 6, 100 ) something like this

But when I was not able to find any example using multidiscrete or tuple space to handle my actions properly.

Anyone knows any example I can try for my custom env.?

python

share|improve this question

asked 5 hours ago

Jake JeongJake Jeong

1

New contributor

Jake Jeong is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

add a comment | 

0

I am trying to implement my custom env. into the openai gym

So far, I am using continuous action space (6 ch)

so input dimension can be used with env.action_space.shape[0]

But I found that it is not stable in my env. I decided to move to multi discrete space like with limited interger values (100, 100, 10, 5, 6, 100 ) something like this

But when I was not able to find any example using multidiscrete or tuple space to handle my actions properly.

Anyone knows any example I can try for my custom env.?

python

share|improve this question

asked 5 hours ago

Jake JeongJake Jeong

1

New contributor

Jake Jeong is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

add a comment | 

I am trying to implement my custom env. into the openai gym

So far, I am using continuous action space (6 ch)

so input dimension can be used with env.action_space.shape[0]

But I found that it is not stable in my env. I decided to move to multi discrete space like with limited interger values (100, 100, 10, 5, 6, 100 ) something like this

But when I was not able to find any example using multidiscrete or tuple space to handle my actions properly.

Anyone knows any example I can try for my custom env.?

python

share|improve this question

asked 5 hours ago

Jake JeongJake Jeong

1

New contributor

Jake Jeong is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

share|improve this question

asked 5 hours ago

Jake JeongJake Jeong

1

New contributor

Jake Jeong is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

share|improve this question

asked 5 hours ago

Jake JeongJake Jeong

1

New contributor

Jake Jeong is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 5 hours ago

Jake JeongJake Jeong

1

New contributor

Jake Jeong is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 5 hours ago

Jake JeongJake Jeong

1