Quanquan Peng

@QuanquanPeng03

PhD @UCSD Prev: @uwcse @SJTU1896

pengqq.com

Joined September 2018

522 Following

407 Followers

Replies Reposts Media

Pinned
Quanquan Peng
@QuanquanPeng03
Aug 12
Children learn to walk by falling. Robots fail too—but we usually throw those failures away. Yet failed rollouts tell us something successful demonstrations cannot: what bad actions actually lead to. So, can robots learn from their failures too? Introducing FACT: Failure-Aware
00:00
15
Quanquan Peng
@QuanquanPeng03
Oct 16
Sim: "astra-hype" Real: Tesla Kudos to the Tesla Team. Hard to believe it actually works in real life!
00:00
Tesla
@Tesla
Oct 16
00:45
Real life, baby
1
Quanquan Peng
@QuanquanPeng03
Oct 13
Do BetaNIST to bring it to the real! Nice work, Octi!
Octi Zhang
@octi_zhang
Oct 13
(1/6) From @GoogleDeepMind’s AlphaGo to AlphaZero, we saw machines find moves that reached beyond what we’d imagined for them. No one taught them those strategies. They emerged from reinforcement learning: playing, failing, and trying again under a single binary task reward for
00:00
Quanquan Peng
@QuanquanPeng03
Oct 13
Hu! 🀄️
Isabella Liu
@Isabella__Liu
Oct 13
Can we scale robot learning without scaling human labor? 📈 Demonstrations, resets, failure recovery, constant supervision—collecting robot data still takes substantial human effort. 🔑 Three keys let agents take on more of the work: 1. Real2Sim2Real: Agents explore and learn
00:00
Quanquan Peng
@QuanquanPeng03
Oct 9
Looks amazing!
Octi Zhang
@octi_zhang
Oct 9
(1/5) Everyone says dexterous manipulation needs real-world data. These policies were trained with none. Our robots mesh gears, thread nuts, and insert pegs zero-shot from RGB, and the same recipe works for locomotion across terrains much harder than before. The missing piece
00:00