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 as a fine-tuning paradigm

22 点作者 ankeshanand超过 3 年前

3 条评论

visarga超过 3 年前
The fruits of massive language modeling are coming to RL. I envision such foundation models becoming cheap and standardized, like an AI operating system. If we could have a cheap, compact, multi-modal GPT-3 chip we could make all sorts of agents run on top. These RL agents would be like the libraries of skills in Matrix, you can load any skill you want on the player.
YetAnotherNick超过 3 年前
In India without VPN:<p>&quot;The website has been blocked as per order of Ministry of Electronics and Information Technology under IT Act, 2000.&quot;
评论 #29911728 未加载
armanboyaci超过 3 年前
&gt; Other learning paradigms are about minimization; reinforcement learning is about maximization.<p>I don&#x27;t see why this is important.
评论 #29911884 未加载
评论 #29904483 未加载
评论 #29911742 未加载