Robert Ormandi

Software Engineer @Google

[Google DeepMind @GoogleDeepMind]

Today our machine learning and distributed computing teams, along with Google Brain, are releasing Launchpad, a system for building distributed machine learning algorithms. Visit https://t.co/Ua86xIIx7s for the code, examples, and some distributed RL agents!

[Gabriel Barth-Maron @gbarthmaron]

Today we released Launchpad, which is what we use for running almost all of our distributed RL experiments at DeepMind. This has been a great project to work on, and we hope the community finds it useful!

[Robert Ormandi @rormandi]

Thank you both @TomBrady (@Buccaneers) and @PatrickMahomes (@Chiefs) for the great game!

[Robert Ormandi @rormandi]

@TomBrady is redefining what it means "I want to make it happen..." #SuperBowlLV #Buccaneers

[Robert Ormandi @rormandi]

Officially congratulations to @TomBrady and the @Buccaneers on winning the #SuperBowlLV #NFL

[Jeff Dean @JeffDean]

On behalf of the entire Google Research & @GoogleAI communities, I'm excited to share an overview of some of our research in 2020.

Thanks to everyone who helped make this work possible!

https://t.co/EYVeQ7PfO4

[TensorFlow @TensorFlow]

⚡️🔋 Supercharge your recommenders

Built-in fast approximate retrieval and improved feature interaction learning are now available in the new release of TensorFlow Recommenders #TFRS.

Learn more → https://t.co/WUCFLWRX5m

[Robert Ormandi @rormandi]

@_arohan_ Oh, yeah, that was a tough one...

[Jeff Dean @JeffDean]

The launch of @TensorFlow ~5 years ago this week was a pretty exciting milestone for a lot of us. We all gathered in a conference room early one morning to watch the original blog post announcing it go live & people start downloading it:

https://t.co/LZpunwFWfx

[Danijar Hafner @danijarh]

What objectives can an intelligent agent optimize?

In this 3 year collab, we categorized the possible objs. APD is a unifying principle that explains repr learning, reward, infogain exploration, empowerment, skill discovery, and niche seeking.

https://t.co/Ja4xxea1M9

👇 Thread

[rohan anil @_arohan_]

Hey twitter ml influencers, can you help fix this? 👇

[Papers with Code @paperswithcode]

🎉 Papers with Code partners with arXiv! Code links are now shown on arXiv articles, and authors can submit code through arXiv. Read more: https://t.co/kO6zhWAWGH

[Robert Ormandi @rormandi]

#TFAgents #RL

[Robert Ormandi @rormandi]

Quite compelling SAC readme with a bunch of interesting empirical data: https://t.co/LECVdDS3KH
from @summeryue0 @tobyjboyd Thank you for putting this together.

[Robert Ormandi @rormandi]

Also @kuanghueilee was heavily involved in this work.

[Jeff Dean @JeffDean]

Looks like Sanjay and I have a few TODO items :) :

https://t.co/ED4HQQcHe1

We are pair programming tomorrow, but already planning to work on something else.

[TensorFlow @TensorFlow]

☝ We have a recommendation for that

Introducing TensorFlow Recommenders, an open-source package that makes building, evaluating, and serving recommender models easy. Find recommendations for movies, restaurants, and much more!

Get started → https://t.co/ydGyCZgMxT

[NumPy @numpy_team]

The NumPy paper is out!

https://t.co/q2Svekk9G8

[Brandon Amos @brandondamos]

In our new paper we scale model-based reinforcement learning to the gym humanoid by using short-horizon model rollouts followed by a learned model-free value estimate.

Paper: https://t.co/UytqwsqKdz
Videos: https://t.co/cjZ60UJg6Z

With @sam_d_stanton @denisyarats @andrewgwils