Junhyuk Oh

Chief Research Officer at Ineffable Intelligence

Previously Research Scientist at DeepMind

[Junhyuk Oh @junh_oh]

Work done with the amazing team: @iurii_kemaev [tech lead], @greg_far, @dancalian, @luisa_zintgraf, @matteohessel, Satinder Singh, @hado, David Silver

Code & weights: https://t.co/Zm3kem2SOl
Paper: https://t.co/3V4TmPTWm4

[Junhyuk Oh @junh_oh]

Excited to announce that our work on “Discovering state-of-the-art RL algorithms” is finally published in @Nature! In this work, we meta-learned RL algorithms at scale.

Paper: https://t.co/3V4TmPTWm4
Blog: https://t.co/G65ReK2iMs

See thread 👇

[Junhyuk Oh @junh_oh]

What did it discover? DiscoRL discovered entirely new prediction semantics.

While humans rely on concepts like "value functions," DiscoRL learned to predict salient future events - like high rewards or changes in policy entropy - that complement traditional RL concepts.

[Luisa Zintgraf @luisa_zintgraf]

Excited to share our new paper, "DataRater: Meta-Learned Dataset Curation"!

We explore a fundamental question: How can we *automatically* learn which data is most valuable for training foundation models?

Paper: https://t.co/N2ozU2RXWb to appear @NeurIPSConf

Thread 👇

[Junhyuk Oh @junh_oh]

I will be briefly talking about how I used JAX to implement my recent #NeurIPS2020 work on Discovering RL Algorithms (https://t.co/Pc74kYMkVo). Stop by our livestream if you are interested. :)

[Google DeepMind @GoogleDeepMind]

Join our team at the #NeurIPS2020 JAX Ecosystem meet up to learn more about JAX and why it's effective for research in reinforcement learning, GANs, meta-gradients and more.

Today at 11am PST / 2pm ET/ 7pm GMT
https://t.co/ORApnkq7pC (calendar invite)

[Marc G. Bellemare @marcgbellemare]

Our most recent work is out in Nature! We're reporting on (reinforcement) learning to navigate Loon stratospheric balloons and minimizing the sim2real gap. Results from a 39-day Pacific Ocean experiment show RL keeps its strong lead in real conditions. https://t.co/jBbCABc3pP

[Google DeepMind @GoogleDeepMind]

In a major scientific breakthrough, the latest version of #AlphaFold has been recognised as a solution to one of biology's grand challenges - the “protein folding problem”. It was validated today at #CASP14, the biennial Critical Assessment of protein Structure Prediction (1/3)

[Berkeley AI Research @berkeley_ai]

CfP for the @iclr2019 workshop on structure and priors in reinforcement learning (SPiRL), deadline 3/7! https://t.co/KAl7Lp1tMy

[Pablo Samuel Castro @pcastr]

really happy to announce the next version of our #RL framework: Dopamine 2.0!
beyond atari: now we support general discrete-domain gym environments.
we've been using this internally for our research and it allows us to test out new ideas very quickly.
try it out!

[Google DeepMind @GoogleDeepMind]

Join us and @Blizzard_Ent this Thursday at 6:00pm GMT for an exciting #StarCraft demonstration, hosted by @Artosis and @RotterdaM08!

Livestream on YouTube: https://t.co/lQytLEsT0o

Read more about #StarCraft2 as an environment for AI research: https://t.co/TSUdS9vttG

[Demis Hassabis @demishassabis]

Delighted to welcome reinforcement learning pioneer Satinder Singh to @DeepMindAI. He’ll bring some incredible experience to the team and I'm really looking forward to working with him!

[Vincent François-Lavet @VinFL]

Excited to share a quite extensive introduction to deep reinforcement learning! With @astro_pyotr @riashatislam @marcgbellemare and Joelle Pineau, we hope it will be useful to the community. Print version available at #NeurIPS! https://t.co/IbGAbNX8do

[Miles Brundage @Miles_Brundage]

"Self-Imitation Learning," Oh and Guo et al.: https://t.co/ryPW9Qf0A2

Imitating past good experiences in the replay buffer leads to big improvements over A2C, PPO, inc. good Montezuma performance in fewer frames than prior approaches

[Pieter Abbeel @pabbeel]

NIPS Deep RL Symposium Schedule now available: https://t.co/a2UEG3v7lf
includes over 70 contributed papers/posters, and invited talks by David Silver, Joelle Pineau, Ruslan @rsalakhu , Ben Van Roy, Michael Bowling. Thursday 12/7 @NipsConference

[Pieter Abbeel @pabbeel]

NIPS Deep RL Symposium deadline Fri Nov 3. We welcome your #ICLR Deep RL submissions! (+other recent work)
https://t.co/HJ26Aff3KZ

[Ruben Villegas @RubenEVillegas]

Check out the code (with trained models) for our ICLR 2017 paper on video prediction.
https://t.co/NFvDIxyF1F

[Junhyuk Oh @junh_oh]

@albert_swart Thank you for mentioning my code. :) They will merge Jeff Donahue's code soon. See the following PR: https://t.co/mvUdQnjIuh