Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Whatever happened to training physics based character controllers using RL? This was all the rage a few years ago. Every clip here looks cool af.

29,075 Aufrufe • vor 3 Monaten •via X (Twitter)

11 Kommentare

Profilbild von Chen Tessler @ CoRL
Chen Tessler @ CoRLvor 3 Monaten

still going strong. Check out our latest work GPC:

Profilbild von AVB
AVBvor 3 Monaten

This is really cool 😍

Profilbild von AVB
AVBvor 3 Monaten

Papers in this video:

Profilbild von Carlos DP ✈️ CoRL 2026
Carlos DP ✈️ CoRL 2026vor 3 Monaten

it's still all the rage this year! Check out GPC, SMP, HIL, etc. These are experiments with GPC:

Profilbild von Chandra Shekhar 📟
Chandra Shekhar 📟vor 3 Monaten

peopel who were doing this are now busy minting synthetic data en masse

Profilbild von CIX 🦾
CIX 🦾vor 3 Monaten

We do this with robots with the @rek sim

Profilbild von pgBouncer
pgBouncervor 3 Monaten

If a virtual object knows how to behave in accurately modeled virtual space, it should know how to in reality Then apply a multiverse simulation to train it on all possibly outcomes Insane potential. Something im very interested in

Profilbild von DK
DKvor 3 Monaten

RL slow, RL expensive, RL fails to generalize to edge cases etc

Profilbild von Fajar M Reza
Fajar M Rezavor 3 Monaten

Character-control progress may depend more on real-world physics than prettier demonstrations.

Profilbild von İsmail Keskin
İsmail Keskinvor 3 Monaten

Probably still eating too much resources. The people doing this research were mostly from AAA studios where resources are already tight. Also unlike traditional animation when this fails it fails in miserable ways. Indies could use this though.

Profilbild von Alec
Alecvor 3 Monaten

Been a bit busy, but wanted to jump back here and mention I'm working on exactly this. There's no reason this shouldn't be the future of characters in games.

Ähnliche Videos