View profile

2021 in the Rear-View Mirror - Issue #2

ML Weekly
ML Weekly
As we approach the end of 2021, you may be already off of work and gearing up for the holidays. December is sometimes called the Season of Giving, so let’s take a moment to be thankful for all the contribution to science and humanity over the last year and think about how we can collaborate more.
The highlight of this week was another great contribution from Google researchers that have released Reinforcement Learning Datasets (RLDS) and a collection of tools for recording, replaying, modifying, annotating, and sharing data for sequential decision making, including offline reinforcement learning, learning from demonstrations, and imitation learning. Read more at this issue of ML Weekly!

Source: https://arxiv.org/pdf/2111.02767.pdf
Source: https://arxiv.org/pdf/2111.02767.pdf
🗞 News
RLDS: An Ecosystem to Generate, Share, and Use Datasets in Reinforcement Learning
✍️ Papers
Sergey Levine
What happens if, when we learn a model in RL, we reward the policy for doing things where the model is correct? Turns out that this is (surprisingly) the same as minimizing the number of bits of state that the policy needs access to.

Paper: https://t.co/KIDQOM3iaW

Thread below: https://t.co/9HBbJ9GrnM
📣 Call for Papers
IJCAI-ECAI 2022
🎥 Video
Neurosymbolic Programming by Professor Yisong Yue
🎙 Podcast
Andrej Karpathy on the visionary AI in Tesla's autonomous driving
🕵️ Positions
Lecturer/Senior Lecturer or Reader in Machine Learning and Artificial Intelligence at Bath
Ph.D. in Reliable Uncertainties for Machine Learning at Ulster University
Did you enjoy this issue? Yes No
ML Weekly
ML Weekly @alirezasamar

Machine Learning Weekly is your weekly dose of what's up in machine learning, deep learning, and robotics. Curated in spare time by @alirezasamar to accelerate research.

In order to unsubscribe, click here.
If you were forwarded this newsletter and you like it, you can subscribe here.
Created with Revue by Twitter.
Jõe 7, 10151 Tallinn, Estonia