Per VognsenNew Matthias Müller video just dropped. https://www.youtube.com/watch?v=XmzBREkK8kY
Michiel van de Panne
- 184 Followers
- 46 Following
- 16 Posts
UBC Computer Science; physics-based models of human movement; deep reinforcement learning; animation; robotics;
David BammanI declare ChatGPT to be a performance-enhancing substance for the greatest game: Taboo. All wins with it get an asterisk.
Sumit SanyalWhoooah, can you feel the edifices of the #walledgarden trembling in the footsteps of the mighty #mastodon !
https://www.theguardian.com/technology/2022/dec/21/firefox-and-tumblr-join-rush-to-support-mastodon-social-network
The GradientFor those still figuring out how Mastodon works, here's a handy chart to make it clear!
#mastodon #feditips
Cas [back-up] (@[email protected])
Attached: 1 image Here's a flow chart of how the fediverse works. You don't ever see all of the fediverse from one instance. The vast majority of what you see is people followed by people on your instance. Hashtag searches are limited to that, too. So if you want to make your bit of the fediverse good, you have to: 1) Boost cool stuff to all your followers on other instances, especially if they contain hashtags; 2) Use hashtags. #mastodon #meta #FAQ
Max WoolfMastodon tip: if you want to share a Mastodon post, *always* expand and click "Copy link to post" instead of copying from the URL bar, as the URL bar will be tied to your specific instance.
Amazing talk, describing the Antikythera Mechanism, a mechanical device from ancient Greece, 2200 years ago. via David Deutsch. https://www.youtube.com/watch?v=xWVA6TeUKYU&t=327s
The Antikythera Mechanism: A Shocking Discovery from Ancient Greece.
Belated advertising for our NeurIPS 2022 paper. ReLU-based policies partition the input space into piecewise linear regions. How many regions are there? (Ans: related to # neurons; only weakly related to depth). Does the region density increase in areas that the policy learns to visit? (yes, moderately). See here for other lessons learned: https://www.cs.ubc.ca/~van/papers/2022-NeurIPS-understanding/index.html
#RL
#RL
Useful tool for embedding Mastodon feeds on web pages: http://www.mastofeed.com/
For those who couldn't make it to CoRL 2022 (myself included), all the papers are available here: https://openreview.net/group?id=robot-learning.org/CoRL/2022/Conference
Just a quick reminder of the many interesting talks / interviews on the "Talk RL" podcast: https://www.talkrl.com/
TalkRL: The Reinforcement Learning Podcast
TalkRL podcast is All Reinforcement Learning, All the Time. In-depth interviews with brilliant people at the forefront of RL research and practice. Guests from places like MILA, OpenAI, MIT, DeepMind, Berkeley, Amii, Oxford, Google Research, Brown, Waymo, Caltech, and Vector Institute. Hosted by Robin Ranjit Singh Chauhan.