How to represents states in numeric representation for Reinforcement learning. ( to Create a Q Table )
I am working on a Q-learning algorithm where I need to construct a formula to create a custom colour by mixing many colours. So the objective here is to generate a formula for all valid custom colors
success forumla - merit with a reward
bad formula - punish the agent with demerits
Basically, I have 10 base colours from which I need to generate custom colours. The basic colours are red, green, blue, white, black, yellow, etc
I am encoding these basic colours using one - hot encoding
red here is [1,0,0,0,0,0,0,0,0,0]
green here is [0,1,0,0,0,0,0,0,0,0]
blue here is [0,0,1,0,0,0,0,0,0,0]
white here is [0,0,0,1,0,0,0,0,0,0]
black here is [0,0,0,0,1,0,0,0,0,0]
yellow is [0,0,0,0,0,1,0,0,0,0]
etc,etc
if I want to generate
CASE 1: pink color then it is a mix of red + white ( GOOD FORMULA )
CASE 2: light green colour then it is a mix of green + white ( GOOD FORMULA )
CASE 3: grey colour then it is a mix of black + white ( GOOD FORMULA )
CASE 4: purple colour then it is a mix of pink + black ( GOOD FORMULA )
CASE 5: eggplant colour is purple + green ( GOOD FORMULA )
CASE 6: BAD colour is purple + black ( BAD FORMULA )
I presume, the state is a colour and the action is selecting the other colour resulting in a custom colour.
If the state is one of the base colours, I can represent the state with the colour (using one hot encoding).
But if the state is a custom colour, is there a way to represent this in a numerical representation ? ( for CASE 4 , CASE 5 and CASE 6)
I hope, I made my case as much clear as possible. Since there are 10 base colours, the combinatons are massive and hence the states. Not sure how to proceed from here. Any guidance would be of immense help
reinforcement-learning
add a comment |
I am working on a Q-learning algorithm where I need to construct a formula to create a custom colour by mixing many colours. So the objective here is to generate a formula for all valid custom colors
success forumla - merit with a reward
bad formula - punish the agent with demerits
Basically, I have 10 base colours from which I need to generate custom colours. The basic colours are red, green, blue, white, black, yellow, etc
I am encoding these basic colours using one - hot encoding
red here is [1,0,0,0,0,0,0,0,0,0]
green here is [0,1,0,0,0,0,0,0,0,0]
blue here is [0,0,1,0,0,0,0,0,0,0]
white here is [0,0,0,1,0,0,0,0,0,0]
black here is [0,0,0,0,1,0,0,0,0,0]
yellow is [0,0,0,0,0,1,0,0,0,0]
etc,etc
if I want to generate
CASE 1: pink color then it is a mix of red + white ( GOOD FORMULA )
CASE 2: light green colour then it is a mix of green + white ( GOOD FORMULA )
CASE 3: grey colour then it is a mix of black + white ( GOOD FORMULA )
CASE 4: purple colour then it is a mix of pink + black ( GOOD FORMULA )
CASE 5: eggplant colour is purple + green ( GOOD FORMULA )
CASE 6: BAD colour is purple + black ( BAD FORMULA )
I presume, the state is a colour and the action is selecting the other colour resulting in a custom colour.
If the state is one of the base colours, I can represent the state with the colour (using one hot encoding).
But if the state is a custom colour, is there a way to represent this in a numerical representation ? ( for CASE 4 , CASE 5 and CASE 6)
I hope, I made my case as much clear as possible. Since there are 10 base colours, the combinatons are massive and hence the states. Not sure how to proceed from here. Any guidance would be of immense help
reinforcement-learning
Is the amount of color combinations 10 factorial? Or are the custom colors only a combination of 2 base colors. If it is only a combination of 2 base colors, you can just do multiple hot encoding. Such as pink being [1, 0, 0, 1, 0, ...] to represent both white and red being active.
– Rui Nian
Jan 3 at 14:47
@RuiNian - thanks for your time and help. Deeply appreciate it. The amount of color combinations is 10 factorial. But most ( say 60%) of the color combinations results in bad formula and remaining 40% of color combinations results in good formula.
– Timothy Rajan
Jan 3 at 22:14
add a comment |
I am working on a Q-learning algorithm where I need to construct a formula to create a custom colour by mixing many colours. So the objective here is to generate a formula for all valid custom colors
success forumla - merit with a reward
bad formula - punish the agent with demerits
Basically, I have 10 base colours from which I need to generate custom colours. The basic colours are red, green, blue, white, black, yellow, etc
I am encoding these basic colours using one - hot encoding
red here is [1,0,0,0,0,0,0,0,0,0]
green here is [0,1,0,0,0,0,0,0,0,0]
blue here is [0,0,1,0,0,0,0,0,0,0]
white here is [0,0,0,1,0,0,0,0,0,0]
black here is [0,0,0,0,1,0,0,0,0,0]
yellow is [0,0,0,0,0,1,0,0,0,0]
etc,etc
if I want to generate
CASE 1: pink color then it is a mix of red + white ( GOOD FORMULA )
CASE 2: light green colour then it is a mix of green + white ( GOOD FORMULA )
CASE 3: grey colour then it is a mix of black + white ( GOOD FORMULA )
CASE 4: purple colour then it is a mix of pink + black ( GOOD FORMULA )
CASE 5: eggplant colour is purple + green ( GOOD FORMULA )
CASE 6: BAD colour is purple + black ( BAD FORMULA )
I presume, the state is a colour and the action is selecting the other colour resulting in a custom colour.
If the state is one of the base colours, I can represent the state with the colour (using one hot encoding).
But if the state is a custom colour, is there a way to represent this in a numerical representation ? ( for CASE 4 , CASE 5 and CASE 6)
I hope, I made my case as much clear as possible. Since there are 10 base colours, the combinatons are massive and hence the states. Not sure how to proceed from here. Any guidance would be of immense help
reinforcement-learning
I am working on a Q-learning algorithm where I need to construct a formula to create a custom colour by mixing many colours. So the objective here is to generate a formula for all valid custom colors
success forumla - merit with a reward
bad formula - punish the agent with demerits
Basically, I have 10 base colours from which I need to generate custom colours. The basic colours are red, green, blue, white, black, yellow, etc
I am encoding these basic colours using one - hot encoding
red here is [1,0,0,0,0,0,0,0,0,0]
green here is [0,1,0,0,0,0,0,0,0,0]
blue here is [0,0,1,0,0,0,0,0,0,0]
white here is [0,0,0,1,0,0,0,0,0,0]
black here is [0,0,0,0,1,0,0,0,0,0]
yellow is [0,0,0,0,0,1,0,0,0,0]
etc,etc
if I want to generate
CASE 1: pink color then it is a mix of red + white ( GOOD FORMULA )
CASE 2: light green colour then it is a mix of green + white ( GOOD FORMULA )
CASE 3: grey colour then it is a mix of black + white ( GOOD FORMULA )
CASE 4: purple colour then it is a mix of pink + black ( GOOD FORMULA )
CASE 5: eggplant colour is purple + green ( GOOD FORMULA )
CASE 6: BAD colour is purple + black ( BAD FORMULA )
I presume, the state is a colour and the action is selecting the other colour resulting in a custom colour.
If the state is one of the base colours, I can represent the state with the colour (using one hot encoding).
But if the state is a custom colour, is there a way to represent this in a numerical representation ? ( for CASE 4 , CASE 5 and CASE 6)
I hope, I made my case as much clear as possible. Since there are 10 base colours, the combinatons are massive and hence the states. Not sure how to proceed from here. Any guidance would be of immense help
reinforcement-learning
reinforcement-learning
asked Jan 3 at 1:56
Timothy RajanTimothy Rajan
81652549
81652549
Is the amount of color combinations 10 factorial? Or are the custom colors only a combination of 2 base colors. If it is only a combination of 2 base colors, you can just do multiple hot encoding. Such as pink being [1, 0, 0, 1, 0, ...] to represent both white and red being active.
– Rui Nian
Jan 3 at 14:47
@RuiNian - thanks for your time and help. Deeply appreciate it. The amount of color combinations is 10 factorial. But most ( say 60%) of the color combinations results in bad formula and remaining 40% of color combinations results in good formula.
– Timothy Rajan
Jan 3 at 22:14
add a comment |
Is the amount of color combinations 10 factorial? Or are the custom colors only a combination of 2 base colors. If it is only a combination of 2 base colors, you can just do multiple hot encoding. Such as pink being [1, 0, 0, 1, 0, ...] to represent both white and red being active.
– Rui Nian
Jan 3 at 14:47
@RuiNian - thanks for your time and help. Deeply appreciate it. The amount of color combinations is 10 factorial. But most ( say 60%) of the color combinations results in bad formula and remaining 40% of color combinations results in good formula.
– Timothy Rajan
Jan 3 at 22:14
Is the amount of color combinations 10 factorial? Or are the custom colors only a combination of 2 base colors. If it is only a combination of 2 base colors, you can just do multiple hot encoding. Such as pink being [1, 0, 0, 1, 0, ...] to represent both white and red being active.
– Rui Nian
Jan 3 at 14:47
Is the amount of color combinations 10 factorial? Or are the custom colors only a combination of 2 base colors. If it is only a combination of 2 base colors, you can just do multiple hot encoding. Such as pink being [1, 0, 0, 1, 0, ...] to represent both white and red being active.
– Rui Nian
Jan 3 at 14:47
@RuiNian - thanks for your time and help. Deeply appreciate it. The amount of color combinations is 10 factorial. But most ( say 60%) of the color combinations results in bad formula and remaining 40% of color combinations results in good formula.
– Timothy Rajan
Jan 3 at 22:14
@RuiNian - thanks for your time and help. Deeply appreciate it. The amount of color combinations is 10 factorial. But most ( say 60%) of the color combinations results in bad formula and remaining 40% of color combinations results in good formula.
– Timothy Rajan
Jan 3 at 22:14
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f54015434%2fhow-to-represents-states-in-numeric-representation-for-reinforcement-learning%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f54015434%2fhow-to-represents-states-in-numeric-representation-for-reinforcement-learning%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Is the amount of color combinations 10 factorial? Or are the custom colors only a combination of 2 base colors. If it is only a combination of 2 base colors, you can just do multiple hot encoding. Such as pink being [1, 0, 0, 1, 0, ...] to represent both white and red being active.
– Rui Nian
Jan 3 at 14:47
@RuiNian - thanks for your time and help. Deeply appreciate it. The amount of color combinations is 10 factorial. But most ( say 60%) of the color combinations results in bad formula and remaining 40% of color combinations results in good formula.
– Timothy Rajan
Jan 3 at 22:14