Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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 görüntüleme • 3 ay önce •via X (Twitter)

11 Yorum

Chen Tessler @ CoRL profil fotoğrafı
Chen Tessler @ CoRL3 ay önce

still going strong. Check out our latest work GPC:

AVB profil fotoğrafı
AVB3 ay önce

This is really cool 😍

AVB profil fotoğrafı
AVB3 ay önce

Papers in this video:

Carlos DP ✈️ CoRL 2026 profil fotoğrafı
Carlos DP ✈️ CoRL 20263 ay önce

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

Chandra Shekhar 📟 profil fotoğrafı
Chandra Shekhar 📟3 ay önce

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

CIX 🦾 profil fotoğrafı
CIX 🦾3 ay önce

We do this with robots with the @rek sim

pgBouncer profil fotoğrafı
pgBouncer3 ay önce

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

DK profil fotoğrafı
DK3 ay önce

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

Fajar M Reza profil fotoğrafı
Fajar M Reza3 ay önce

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

İsmail Keskin profil fotoğrafı
İsmail Keskin3 ay önce

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.

Alec profil fotoğrafı
Alec3 ay önce

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.

Benzer Videolar