TalkRL: The Reinforcement Learning Podcast cover image

Jordan Terry

TalkRL: The Reinforcement Learning Podcast

00:00

The Impact of Implementation Specific Tricks on Black Box Optimizers

There are a large amount of implementation specific tricks that impact how black box optimizers are used. For automatic hyper parometer tuning for r l, i think i've written some of the largest amount of automade hyperhamn tuning code in the world. And if anyone wants to have me tell them everything i know about that is detale me. If anyone's interested for reserch shop, i think this is a foundationally important thing that, as far as know, literally knowone in the world is am working on.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app