TalkRL: The Reinforcement Learning Podcast cover image

Robert Lange

TalkRL: The Reinforcement Learning Podcast

NOTE

The Grammar of Language in AI

The paper explores the use of grammar and action grammars to define temporarily extended actions. It distinguishes between macro actions, which are deterministic sequences of primitive actions, and options, which have termination criteria. Unlike options, macro actions are always executed in a deterministic and full sequence. The connection between language and these concepts is intriguing.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner