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。

Q* Approximation for Batch Reinforcement Learning: A Theoretical Comparison

21 点作者 ericzawo超过 1 年前

2 条评论

avallach超过 1 年前
Related from two days ago: <a href="https:&#x2F;&#x2F;www.reuters.com&#x2F;technology&#x2F;sam-altmans-ouster-openai-was-precipitated-by-letter-board-about-ai-breakthrough-2023-11-22&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.reuters.com&#x2F;technology&#x2F;sam-altmans-ouster-openai...</a><p>&quot;Some at OpenAI believe Q* (pronounced Q-Star) could be a breakthrough in the startup&#x27;s search for what&#x27;s known as artificial general intelligence&quot; and &quot;wrote a letter to the board of directors warning [it] could threaten humanity&quot;
blharr超过 1 年前
It seems like people are really stretching here. Q-learning has been a thing for a while now. And in optimization of X<i>, Q</i>, etc. the star is just used to mean the optimal value.
评论 #38416919 未加载