Ttdfjt

A Tale of Snake and Coffee

Can an opamp have its own voltage regulator?

What is the color associated with lukewarm?

Idiom for 'person who gets violent when drunk"

Do items with curse of vanishing disappear from shulker boxes?

Can I appeal credit ding if ex-wife is responsible for paying mortgage?

For Saintsbury, which English novelists constituted the "great quartet of the mid-eighteenth century"?

Does an African-American baby born in Youngstown, Ohio have a higher infant mortality rate than a baby born in Iran?

Can artificial satellite positions affect tides?

Should I worry about having my credit pulled multiple times while car shopping?

Having some issue with notation in a Hilbert space

What is the difference between state-based effects and effects on the stack?

Are soroban (Japanese abacus) classes worth doing?

How did the European Union reach the figure of 3% as a maximum allowed deficit?

My parents claim they cannot pay for my college education; what are my options?

Do legislators hold the right of legislative initiative?

The title "Mord mit Aussicht" explained

What is the context for Napoleon's quote "[the Austrians] did not know the value of five minutes"?

Must a CPU have a GPU if the motherboard provides a display port (when there isn't any separate video card)?

Jam with honey & without pectin has a saucy consistency always

Can an escape pod land on Earth from orbit and not be immediately detected?

What does the output current rating from an H-Bridge's datasheet really mean?

Someone who is granted access to information but not expected to read it

Using roof rails to set up hammock

How Does AlphaGo Zero Implement Reinforcement Learning?

What is self-supervised learning in machine learning?What is experience replay in laymen's terms?AlphaZero chess algorithm, Monte Carlo searchHow to implement a contextual reinforcement learning model?How to implement a constrained action space in reinforcement learning?Would AlphaGo Zero become perfect with enough training time?How does reinforcement learning handle measured disturbances?Rollout algorithm like Monte Carlo search suggest model based reinforcement learning?What is the difference between DQN and AlphaGo Zero?How do the achievements met in the gaming field (ex. AlphaGo Zero) impact other fields of application?Feature Selection using Monte Carlo Tree SearchHow can alpha zero learn if the tree search stops and restarts before finishing a game?

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty margin-bottom:0;

3

$begingroup$

AlphaGo Zero (https://deepmind.com/blog/alphago-zero-learning-scratch/) has several key components that contribute to it's success:

1. A Monte Carlo Tree Search Algorithm that allows it to better search and learn from the state space of Go


2. A Deep Neural Network architecture that learns the value and policies of given states, to better inform the MCTS.

My question is, how is this Reinforcement Learning? Or rather, what aspects of this algorithm specifically make it a Reinforcement Learning problem? Couldn't this just be considered a Supervised Learning problem?

reinforcement-learning monte-carlo-tree-search supervised-learning alphago-zero go

share|improve this question

asked Jun 7 at 16:56

SeeDerekEngineerSeeDerekEngineer

2148

$endgroup$

add a comment | 

3

$begingroup$

AlphaGo Zero (https://deepmind.com/blog/alphago-zero-learning-scratch/) has several key components that contribute to it's success:

1. A Monte Carlo Tree Search Algorithm that allows it to better search and learn from the state space of Go


2. A Deep Neural Network architecture that learns the value and policies of given states, to better inform the MCTS.

My question is, how is this Reinforcement Learning? Or rather, what aspects of this algorithm specifically make it a Reinforcement Learning problem? Couldn't this just be considered a Supervised Learning problem?

reinforcement-learning monte-carlo-tree-search supervised-learning alphago-zero go

share|improve this question

asked Jun 7 at 16:56

SeeDerekEngineerSeeDerekEngineer

2148

$endgroup$

add a comment | 

$begingroup$

AlphaGo Zero (https://deepmind.com/blog/alphago-zero-learning-scratch/) has several key components that contribute to it's success:

1. A Monte Carlo Tree Search Algorithm that allows it to better search and learn from the state space of Go


2. A Deep Neural Network architecture that learns the value and policies of given states, to better inform the MCTS.

My question is, how is this Reinforcement Learning? Or rather, what aspects of this algorithm specifically make it a Reinforcement Learning problem? Couldn't this just be considered a Supervised Learning problem?

reinforcement-learning monte-carlo-tree-search supervised-learning alphago-zero go

share|improve this question

asked Jun 7 at 16:56

SeeDerekEngineerSeeDerekEngineer

2148

$endgroup$

share|improve this question

asked Jun 7 at 16:56

SeeDerekEngineerSeeDerekEngineer

2148

share|improve this question

asked Jun 7 at 16:56

SeeDerekEngineerSeeDerekEngineer

2148

asked Jun 7 at 16:56

SeeDerekEngineerSeeDerekEngineer

2148

asked Jun 7 at 16:56

SeeDerekEngineerSeeDerekEngineer

2148

1 Answer
1

active

oldest

votes

3

$begingroup$

If you learn a policy or a value function from experience (that is, interaction with an environment), that's RL. In the case of AlphaGo, the MCTS is used to acquire the experience.

RL could in fact be considered supervised learning (SL) or, more specifically, self-supervised learning, where the experience corresponds to the labels in SL, especially nowadays with techniques like experience replay.

share|improve this answer

edited Jun 7 at 17:28

answered Jun 7 at 17:21

nbronbro

4,0562827

$endgroup$

add a comment | 

Your Answer

StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "658"
;
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: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
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
,
noCode: true, onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);



);

draft saved

draft discarded

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

Name

Email

Required, but never shown

StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fai.stackexchange.com%2fquestions%2f12739%2fhow-does-alphago-zero-implement-reinforcement-learning%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

3

$begingroup$

If you learn a policy or a value function from experience (that is, interaction with an environment), that's RL. In the case of AlphaGo, the MCTS is used to acquire the experience.

RL could in fact be considered supervised learning (SL) or, more specifically, self-supervised learning, where the experience corresponds to the labels in SL, especially nowadays with techniques like experience replay.

share|improve this answer

edited Jun 7 at 17:28

answered Jun 7 at 17:21

nbronbro

4,0562827

$endgroup$

add a comment | 

3

$begingroup$

If you learn a policy or a value function from experience (that is, interaction with an environment), that's RL. In the case of AlphaGo, the MCTS is used to acquire the experience.

RL could in fact be considered supervised learning (SL) or, more specifically, self-supervised learning, where the experience corresponds to the labels in SL, especially nowadays with techniques like experience replay.

share|improve this answer

edited Jun 7 at 17:28

answered Jun 7 at 17:21

nbronbro

4,0562827

$endgroup$

add a comment | 

$begingroup$

If you learn a policy or a value function from experience (that is, interaction with an environment), that's RL. In the case of AlphaGo, the MCTS is used to acquire the experience.

RL could in fact be considered supervised learning (SL) or, more specifically, self-supervised learning, where the experience corresponds to the labels in SL, especially nowadays with techniques like experience replay.

share|improve this answer

edited Jun 7 at 17:28

answered Jun 7 at 17:21

nbronbro

4,0562827

$endgroup$

share|improve this answer

edited Jun 7 at 17:28

answered Jun 7 at 17:21

nbronbro

4,0562827

answered Jun 7 at 17:21

nbronbro

4,0562827

answered Jun 7 at 17:21

nbronbro

4,0562827