April 2020
Intermediate to advanced
816 pages
18h 32m
Chinese
Content preview from 精通機器學習
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
638
|
第十八章：強化學習
Curiosity-based exploration (https://homl.info/curiosity)
27
獎勵的稀疏性是
RL
領域反復出現的問題
，
它會讓學習速度非常緩慢且低效
。Deepak
Pathak
和其他的
UC Berkeley
研究員提出一種振奮人心的方式來解決這種問題
：
何不
忽略獎勵
，
直接讓
agent
極度好奇地探索環境
？
如此一來
，
獎勵就變成
agent
固有的東
西
，
而不是來自環境的東西
。
類似的情況
，
激發孩子的好奇心比單純鼓勵孩子取得好
成績更可能帶來好結果
。
這是如何運作的
？ agent
會不斷試著預測行動的結果
，
並積
極尋找結果與預測不一樣的情況
。
換句話說
，
他喜歡驚奇
。
如果結果是可預測的
（
無
聊
），
它就會去別的地方
。
但是
，
如果結果是不可預測的
，
但是
agent
發現自己無法控
制它
，
過一段時間之後
，agent
也會感到厭煩
。
作者們單憑好奇心就成功地訓練了一個
agent
來玩許多遊戲
：
雖然
agent
在輸掉遊戲時不會受到懲罰
，
但遊戲會重新開始
，
這
是件無聊的事
，
所以它會學習避免這件事的發生
。
本章探討許多主題
：
策略梯度
、
馬可夫鏈
、
馬可夫決策過程
、Q-Learning、Approximate
Q-Learning、Deep Q-Learning
與它的主要變體
（
固定
Q
值目標
、Double DQN、Dueling
DQN，
以及經驗重播優先排序
）
我們探討了如何使用
TF-Agents
來大規模訓練
agent，
最
後簡單看了一些其他的熱門演算法
。
強化學習是龐大且刺激的領域
，
每天都有新的點子和 ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.