【DL輪読会】Implicit Behavioral Cloning

135 Views

May 13, 22

スライド概要

2022/05/13
Deep Learning JP:
http://deeplearning.jp/seminar-2/

シェア

またはPlayer版

埋め込む »CMSなどでJSが使えない場合

関連スライド

各ページのテキスト
1.

DEEP LEARNING JP [DL Papers] Implicit Behavioral Cloning (CoRL 2021) Koki Yamane, University of Tsukuba http://deeplearning.jp/ 1

2.

◼ Implicit Behavioral Cloning ◼ CoRL 2021 ◼ Robotics at Google  Pete Florence, Corey Lynch, Andy Zeng, Oscar Ramirez, Ayzaan Wahid, Laura Downs, Adrian Wong, Johnny Lee, Igor Mordatch, Jonathan Tompson ◼ https://implicitbc.github.io/ 2022/5/13 2

3.

(BC) 2022/5/13 EBM 3

4.

Behavior Cloning ෝ = 𝑭𝜽 𝒐 𝒂 ◼  ◼  ◼ 2022/5/13 4

5.

BC Explicit Model ( ෝ = 𝑭𝜽 𝒐 𝒂 2022/5/13 ) Implicit Model ( ) ෝ = argmin 𝑬𝜽 𝒐, 𝒂 𝒂 5

6.

ෝ = argmin 𝑬𝜽 𝒐, 𝒂 𝒂 𝑁 𝐿InfoNCE = ෍ −log 𝑝෦𝜃 𝑦𝑖 |𝑥, 𝑖=0 𝑝෦𝜃 𝑦𝑖 |𝑥, 2022/5/13 𝑗 𝑁𝑛𝑒𝑔 𝑦෤𝑖 𝑗=1 𝑒 −𝐸𝜃 = 𝑒 −𝐸𝜃 𝑥𝑖,𝑦𝑖 + 𝑗 𝑁𝑛𝑒𝑔 𝑦෤𝑖 𝑗=1 𝑥𝑖 ,𝑦𝑖 𝑁𝑛𝑒𝑔 −𝐸𝜃 𝑥𝑖 ,𝑦෤ 𝑗 𝑖 σ𝑗=1 𝑒 6

7.

(CNN+) MLP 2022/5/13 7

8.

Implicit Model 2022/5/13 8

9.

Implicit Model 2022/5/13 9

10.

Implicit Model 2022/5/13 10

11.

2022/5/13 11

12.

Bi-Manual Sweeping Task Explicit Model ( 2022/5/13 ) Implicit Model ( ) 12

13.

Insertion Task Explicit Model ( 2022/5/13 ) Implicit Model ( ) 13

14.

Sorting Task Explicit Model ( 2022/5/13 ) Implicit Model ( ) 14

15.

◼ BC EBM ◼ ◼ ◼   RNN 2022/5/13 15