Wow! This is amazing. A few years ago RL was starting to be applied in the robotics domain, with many doubters. Fast forward a handful of years and this!
https://twitter.com/OpenAI/status/1184135128869527552 …
-
0:18 -
Replying to @ShamKakade6
Dagmar Monett Retweeted Gary Marcus
FYI, a dose of reality by the accurate
#AI#hype watcher@GaryMarcus:https://twitter.com/GaryMarcus/status/1184299965390053377?s=09 …Dagmar Monett added,
Gary Marcus @GaryMarcus#DeepLearning#hype alert: @OpenAI’s paper on Rubik’s cube solving starts “We’ve trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand”; mentions critical hardwired symbol-manipulating cube solver only at ref. 111 https://openai.com/blog/solving-rubiks-cube/ …1 reply 0 retweets 3 likes -
Replying to @dmonett @GaryMarcus
Many roboticists and RL researchers, including myself, consider this to have pushed the state-of-the-art in robotics/manipulation because dextrous hand manipulation is challenging, as is sim2real. I am impressed. (solving the rubics cube itself is not relevant).
1 reply 0 retweets 2 likes
i actually agree (mostly) with this, though the bluetooth sensors etc undermine it a little bit. again my objection is not with the research but with the framing.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.