HackerTrans
トップ新着トレンドコメント過去質問紹介求人

siekmanj

no profile record

投稿

Agility’s Latest Digit Robot Prepares for Its First Job

spectrum.ieee.org
1 ポイント·投稿者 siekmanj·3 年前·0 コメント

Bipedal robot developed at Oregon State achieves 100m Guinness World Record

today.oregonstate.edu
7 ポイント·投稿者 siekmanj·4 年前·1 コメント

Agility Robotics Raises $150M

agilityrobotics.com
1 ポイント·投稿者 siekmanj·4 年前·0 コメント

コメント

siekmanj
·3 年前·議論
"RL: A Deep Reinforcement Learning Framework" seems to have been hallucinated, does not exist.
siekmanj
·4 年前·議論
Video here: https://twitter.com/oregonstatenews/status/15747969243260108...
siekmanj
·4 年前·議論
https://archive.ph/8X76D
siekmanj
·4 年前·議論
True, but it's not trying to be multi-threaded, just concurrent.
siekmanj
·4 年前·議論
Python has actually had concurrency since about 2019: https://docs.python.org/3/library/asyncio.html. Having used it a few times, it seems fairly sane, but tbf my experience with concurrency in other languages is fairly limited.

edit: ray https://github.com/ray-project/ray is also pretty easy to use and powerful for actual parallelism
siekmanj
·4 年前·議論
From some cursory googling:

Afghanistan peak US troops: 102,000 (2011)

Gulf war peak US troops: 700,000 (1990-1991)

Iraq peak US troops: range from 168,000 - 192,000 (2007)

Vietnam peak US troops: 543,000 (1969)

Korea peak US troops: 320,000, unclear what year

edit: obviously, Russia's involvement in Ukraine over the last few days would be by far the biggest operation in Europe since WW2. Just not globally (by a long shot).
siekmanj
·5 年前·議論
This is an amazing outcome. The license cost was a huge barrier to entry and the progress of deep RL generally.
siekmanj
·5 年前·議論
The sim2real approach can work pretty well as long as you are very in tune with where your simulator falls short relative to the real world and take steps to circumvent those shortcomings.

Here's some work my lab did on sim2real for a roughly human-scale bipedal robot (Cassie): https://www.youtube.com/watch?v=MPhEmC6b6XU

We were able to train the robot to climb stairs completely by feel/proprioception without any sort of vision. We trained it in simulation, and then transferred it to the real world without issue.