TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Disengage your autopilot – a lesson from reinforcement learning

6 pointsby jinayabout 1 year ago

1 comment

082349872349872about 1 year ago
&gt; <i>humans are notoriously bad at generating random numbers</i><p>Shannon was able to model humans (choosing &quot;heads&quot; or &quot;tails&quot;) effectively with only a 3-bit history, which he encoded in relays, having done so around the middle of last century.<p>Note that recombination is a population&#x27;s way of balancing exploitation and exploration.
评论 #40109683 未加载