TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Reinforcement Learning Progress

39 点作者 rloomba将近 7 年前

1 comment

throwawayjava将近 7 年前
<i>&gt; ...and a really good simulated environment that captures the problem you’re solving.</i><p>The original &quot;data is the new oil&quot; quote was pointing out that raw data, like raw oil, requires lots of processing&#x2F;refinement before the raw resource becomes something with a lot of economic value and potential [1].<p>In that sense, simulated environments are the oil of deep RL.<p>Deep RL has a lot of promise (and obv is already delivering on that promise). But when it comes to the need for high-fidelity and accurate models, we&#x27;re out of the frying pan and into the fire.<p>[1] <a href="https:&#x2F;&#x2F;medium.com&#x2F;@TalPerry&#x2F;on-labeled-data-85fbaf1bdf89" rel="nofollow">https:&#x2F;&#x2F;medium.com&#x2F;@TalPerry&#x2F;on-labeled-data-85fbaf1bdf89</a>