Loading video...

Video Failed to Load

Go Home

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 views • 3 months ago •via X (Twitter)

11 Comments

Chen Tessler @ CoRL's profile picture
Chen Tessler @ CoRL3 months ago

still going strong. Check out our latest work GPC:

AVB's profile picture
AVB3 months ago

This is really cool 😍

AVB's profile picture
AVB3 months ago

Papers in this video:

Carlos DP ✈️ CoRL 2026's profile picture
Carlos DP ✈️ CoRL 20263 months ago

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

Chandra Shekhar 📟's profile picture
Chandra Shekhar 📟3 months ago

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

CIX 🦾's profile picture
CIX 🦾3 months ago

We do this with robots with the @rek sim

pgBouncer's profile picture
pgBouncer3 months ago

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's profile picture
DK3 months ago

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

Fajar M Reza's profile picture
Fajar M Reza3 months ago

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

İsmail Keskin's profile picture
İsmail Keskin3 months ago

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's profile picture
Alec3 months ago

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.

Related Videos