reinforcement learning when there are more than one decision to learn
up vote
0
down vote
favorite
Is there any work on how to learn more than one decision in reinforcement learning? For instance, a firm may want to know how to set optimal price and how to replenish products from suppliers at the same time. In that case, the agent in the RL needs to learn both policies at the same time. Any algorithm could achieve this goal?
I tried searching for multiple policy, multiple agents, and multiple objects. But I am not sure whether they are the right way to solve the issue.
reinforcement-learning
asked Nov 22 at 5:19
Tracy Yang
94213
|
show 1 more comment
up vote
0
down vote
favorite
Is there any work on how to learn more than one decision in reinforcement learning? For instance, a firm may want to know how to set optimal price and how to replenish products from suppliers at the same time. In that case, the agent in the RL needs to learn both policies at the same time. Any algorithm could achieve this goal?
I tried searching for multiple policy, multiple agents, and multiple objects. But I am not sure whether they are the right way to solve the issue.
reinforcement-learning
asked Nov 22 at 5:19
Tracy Yang
94213
I think you should think about the reward design. I suggest you to think about your constrains and design a function that can compose both of your decision
– Daniel Chepenko
Nov 23 at 16:51
@DanielChepenko I think I have an idea of the reward structure. Suppose we have a firm hoping to know optimal pricing, replenishment policy and product assignment. The actions will affect both current reward the state transition, and the behavior of customers in the future.
– Tracy Yang
Nov 23 at 23:40
But why do you want to store it one model?
– Daniel Chepenko
Nov 26 at 18:46
@DanielChepenko cuz those policies, eg pricing, replenishment, ect. might be related to each other. For instance, the price affects how fast products will be sold, which in turn affects when shall I re-order. Do you have any suggestion how I could formulate the problem?
– Tracy Yang
Nov 28 at 19:51
@TracyYang, maybe Multiobjective Reinforcement Learning could be interesting for you. I think the general approach is closer to learn a unique policy that trade-off different objectives, instead of having different policies, as you suggest. Good luck!
– Pablo EM
Dec 8 at 18:39
|
show 1 more comment
up vote
0
down vote
favorite
up vote
0
down vote
favorite
Is there any work on how to learn more than one decision in reinforcement learning? For instance, a firm may want to know how to set optimal price and how to replenish products from suppliers at the same time. In that case, the agent in the RL needs to learn both policies at the same time. Any algorithm could achieve this goal?
I tried searching for multiple policy, multiple agents, and multiple objects. But I am not sure whether they are the right way to solve the issue.
reinforcement-learning
asked Nov 22 at 5:19
Tracy Yang
94213
Is there any work on how to learn more than one decision in reinforcement learning? For instance, a firm may want to know how to set optimal price and how to replenish products from suppliers at the same time. In that case, the agent in the RL needs to learn both policies at the same time. Any algorithm could achieve this goal?
I tried searching for multiple policy, multiple agents, and multiple objects. But I am not sure whether they are the right way to solve the issue.
reinforcement-learning
reinforcement-learning
asked Nov 22 at 5:19
Tracy Yang
94213
asked Nov 22 at 5:19
Tracy Yang
94213
asked Nov 22 at 5:19
Tracy Yang
94213
asked Nov 22 at 5:19
Tracy Yang
94213
asked Nov 22 at 5:19
Tracy Yang
94213
94213
I think you should think about the reward design. I suggest you to think about your constrains and design a function that can compose both of your decision
– Daniel Chepenko
Nov 23 at 16:51
@DanielChepenko I think I have an idea of the reward structure. Suppose we have a firm hoping to know optimal pricing, replenishment policy and product assignment. The actions will affect both current reward the state transition, and the behavior of customers in the future.
– Tracy Yang
Nov 23 at 23:40
But why do you want to store it one model?
– Daniel Chepenko
Nov 26 at 18:46
@DanielChepenko cuz those policies, eg pricing, replenishment, ect. might be related to each other. For instance, the price affects how fast products will be sold, which in turn affects when shall I re-order. Do you have any suggestion how I could formulate the problem?
– Tracy Yang
Nov 28 at 19:51
@TracyYang, maybe Multiobjective Reinforcement Learning could be interesting for you. I think the general approach is closer to learn a unique policy that trade-off different objectives, instead of having different policies, as you suggest. Good luck!
– Pablo EM
Dec 8 at 18:39
|
show 1 more comment
I think you should think about the reward design. I suggest you to think about your constrains and design a function that can compose both of your decision
– Daniel Chepenko
Nov 23 at 16:51
@DanielChepenko I think I have an idea of the reward structure. Suppose we have a firm hoping to know optimal pricing, replenishment policy and product assignment. The actions will affect both current reward the state transition, and the behavior of customers in the future.
– Tracy Yang
Nov 23 at 23:40
But why do you want to store it one model?
– Daniel Chepenko
Nov 26 at 18:46
@DanielChepenko cuz those policies, eg pricing, replenishment, ect. might be related to each other. For instance, the price affects how fast products will be sold, which in turn affects when shall I re-order. Do you have any suggestion how I could formulate the problem?
– Tracy Yang
Nov 28 at 19:51
@TracyYang, maybe Multiobjective Reinforcement Learning could be interesting for you. I think the general approach is closer to learn a unique policy that trade-off different objectives, instead of having different policies, as you suggest. Good luck!
– Pablo EM
Dec 8 at 18:39
I think you should think about the reward design. I suggest you to think about your constrains and design a function that can compose both of your decision
– Daniel Chepenko
Nov 23 at 16:51
I think you should think about the reward design. I suggest you to think about your constrains and design a function that can compose both of your decision
– Daniel Chepenko
Nov 23 at 16:51
@DanielChepenko I think I have an idea of the reward structure. Suppose we have a firm hoping to know optimal pricing, replenishment policy and product assignment. The actions will affect both current reward the state transition, and the behavior of customers in the future.
– Tracy Yang
Nov 23 at 23:40
@DanielChepenko I think I have an idea of the reward structure. Suppose we have a firm hoping to know optimal pricing, replenishment policy and product assignment. The actions will affect both current reward the state transition, and the behavior of customers in the future.
– Tracy Yang
Nov 23 at 23:40
But why do you want to store it one model?
– Daniel Chepenko
Nov 26 at 18:46
But why do you want to store it one model?
– Daniel Chepenko
Nov 26 at 18:46
@DanielChepenko cuz those policies, eg pricing, replenishment, ect. might be related to each other. For instance, the price affects how fast products will be sold, which in turn affects when shall I re-order. Do you have any suggestion how I could formulate the problem?
– Tracy Yang
Nov 28 at 19:51
@DanielChepenko cuz those policies, eg pricing, replenishment, ect. might be related to each other. For instance, the price affects how fast products will be sold, which in turn affects when shall I re-order. Do you have any suggestion how I could formulate the problem?
– Tracy Yang
Nov 28 at 19:51
@TracyYang, maybe Multiobjective Reinforcement Learning could be interesting for you. I think the general approach is closer to learn a unique policy that trade-off different objectives, instead of having different policies, as you suggest. Good luck!
– Pablo EM
Dec 8 at 18:39
@TracyYang, maybe Multiobjective Reinforcement Learning could be interesting for you. I think the general approach is closer to learn a unique policy that trade-off different objectives, instead of having different policies, as you suggest. Good luck!
– Pablo EM
Dec 8 at 18:39
|
show 1 more comment
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',
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%2f53424319%2freinforcement-learning-when-there-are-more-than-one-decision-to-learn%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
active
oldest
votes
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.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- 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%2f53424319%2freinforcement-learning-when-there-are-more-than-one-decision-to-learn%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
I think you should think about the reward design. I suggest you to think about your constrains and design a function that can compose both of your decision
– Daniel Chepenko
Nov 23 at 16:51
@DanielChepenko I think I have an idea of the reward structure. Suppose we have a firm hoping to know optimal pricing, replenishment policy and product assignment. The actions will affect both current reward the state transition, and the behavior of customers in the future.
– Tracy Yang
Nov 23 at 23:40
But why do you want to store it one model?
– Daniel Chepenko
Nov 26 at 18:46
@DanielChepenko cuz those policies, eg pricing, replenishment, ect. might be related to each other. For instance, the price affects how fast products will be sold, which in turn affects when shall I re-order. Do you have any suggestion how I could formulate the problem?
– Tracy Yang
Nov 28 at 19:51
@TracyYang, maybe Multiobjective Reinforcement Learning could be interesting for you. I think the general approach is closer to learn a unique policy that trade-off different objectives, instead of having different policies, as you suggest. Good luck!
– Pablo EM
Dec 8 at 18:39