Name: TensorFlowの内部: TF-エージェント (Inside TensorFlow: TF-Agents)
Uploaded: 2021-01-14T10:50:25.000Z
Duration: 49 min 59 s
Description: VoiceTubeの動画で発音を聞きながら英語表現を覚えよう！学べる英語：

And we'll talk to you guys about our project.

TF-Agents is our reinforcement Learning library

We packaged it with a lot of Colabs, examples,

and documentation to try and make it easy for people

And we use it internally to actually solve

a lot of difficult tasks with reinforcement learning.

In our experience, it's been pretty easy to develop new RL

making it easy to configure and reproduce results.

A lot of this wouldn't be possible without everyone's

contribution, so I just want to make it clear,

People have come and gone within the team, as well.

And so this is right now the biggest chunk

of the current team that is working on TF-Agents.

With that, I'll let Sergio talk a bit more about RL in general.

So we're going to focus a little more about reinforcement

learning and how this is different from other kinds

of machine learning-- unsupervised learning,

And the other one is a recommendation system.

so if you were to try to teach someone how to walk,

it's very difficult, because it's really difficult for me

to explain to you what you need to do to be able to walk--

coordinate your legs, in this case, of the robot-- or even

How you teach someone how to walk is really difficult.

You get up, and then you learn as you're falling.

And that's basically-- you can think of it like the reward

You get a positive reward or a negative reward

So here, you can see also, even with the neural algorithms,

After a few trials of learning, this robot

is able to move around, wobble a little bit, and then fall.

But now he can control the legs a little more.

Not quite walk, but doing better than before.

is able to walk from one place to another,

basically go to a specific location, and all those things.

So how this happen basically is summarizing this code.

Well, there's a lot of code, but overall, the presentation

Basically, we're summarizing all the pieces

you will need to be able to train a model like this,

and how that is different, basically, for other cases?

is trying to play, in this case, or interact

to move the paddle to the left or to the right to hit the ball

It can basically process them for observation,

generate a new action-- like whether to move the paddle

And then based on that, they will get some reward.

it will learn from this environment how to play.

is the main difference between supervised learning

and reinforcement learning-- is that for supervised learning,

字幕リスト動画再生

TensorFlowの内部: TF-エージェント (Inside TensorFlow: TF-Agents)

bunch

critical

multiple

recommend