@svlevine : RT-1 and RT-2 showed the power of large Transformer policies, but relied on imitation learning. Can we trained them with RL? Q-Transformer is "RT + RL" -- a robot Transformer trained with offline RL! Based on CQL, Q-T enables robot Transformers to use suboptimal data. 🧵👇 • TwiCopy

Sergey Levine

@svlevine

+ Follow

Associate Professor at UC Berkeley
Co-founder, Physical Intelligence

ID: 990433714948661250

linkhttp://rail.eecs.berkeley.edu/ calendar_today29-04-2018 03:32:53

2,2K Tweet

84,84K Takipçi

122 Takip Edilen

Sergey Levine

@svlevine

a year ago

RT-1 and RT-2 showed the power of large Transformer policies, but relied on imitation learning. Can we trained them with RL? Q-Transformer is "RT + RL" -- a robot Transformer trained with offline RL! Based on CQL, Q-T enables robot Transformers to use suboptimal data. 🧵👇

thumb_up_off_alt288

chat_bubble_outline7

repeat54

shareShare