Off-Line, Off-Policy RL for Real-World Decision Making at Facebook - #448

episode

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) not yet transcribed

▲ 0

Transcript

This episode hasn't been transcribed yet Upvotes decide what gets transcribed next — 0 so far. Sign in to upvote

Related

recent transcribed audio

Transrapid, Flugtaxis, Hyperloop – Warum es neuartige Verkehrstechnik so schwer hat 28 min · 22 Sep 2026 · Das Wissen | SWR

In The Lab: Who Dares To Dance With Destiny 29 min · 22 Sep 2026 · Dan Does Footy

Fletch, Vaughan & Hayley's Lil Bitta Pod - 22nd September 2026 6 min · 22 Sep 2026 · ZM's Fletch, Vaughan & Hayley

By Order of the Faithfuls: Celebs? Don’t Need Them! (The Traitors: New Blood Recap) 1h 0m · 22 Sep 2026 · Two Ts In A Pod with Teddi Mellencamp and Tamra Judge

NPR News: 09-21-2026 8PM EDT 4 min · 22 Sep 2026 · NPR News Now

Alistair Nicholson in the studio! - AFL Coaches Association Senior Coach of the Year award | AFLCA CEO (22.09.26) 11 min · 22 Sep 2026 · Whateley

Report any issue

Source

Recorded18 Jan 2021

Publisherfeeds.megaphone.fm ↗

Handlerec:12496089

Show notes

Today we’re joined by Jason Gauci, a Software Engineering Manager at Facebook AI. In our conversation with Jason, we explore their Reinforcement Learning platform, Re-Agent (Horizon). We discuss the role of decision making and game theory in the platform and the types of decisions they’re using Re-Agent to make, from ranking and recommendations to their eCommerce marketplace. Jason also walks us through the differences between online/offline and on/off policy model training, and where Re-Agent sits in this spectrum. Finally, we discuss the concept of counterfactual causality, and how they ensure safety in the results of their models. The complete show notes for this episode can be found at twimlai.com/go/448.

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.

Sign in