Excited to share what I've been working on these last few months! Spinning Up in Deep RL, an educational resource that we hope can bring down the barrier to entry in RL. spinningup.openai.com/en/latest/ blog.openai.com/spinning-up-in…

The dedication 👌 milamontreal Microsoft Research

This book is a must read for anyone interested in AI, machine learning, and machine vision. b-gat.es/2QKbHxi

We can now measure a priori how well a deep learning model will parallelize during training. Super pumped that this work uses Dota as a research platform: x.com/openai/status/…

I am an optimist. For me that means that I’m inspired to look for people making progress, and to help spread that progress as widely as possible. Here are some of those areas. b-gat.es/2QRcKeH

“A Holiday Reading List to Satisfy Your Inner Nerd” by integrate.ai link.medium.com/VQB8BzqZMS

🎉🇨🇦 Congratulations to the godfather of Deep Learning, AI pioneer and Google Engineering Fellow Geoffrey Hinton on being named a Companion of the #OrderofCanada. Google AI University of Toronto

This is one of my favorite infographics. A lot of people underestimate just how much life has improved over the last two centuries: b-gat.es/2S23hlG

“The way how Deepmind beat the human pros was in direct contradiction to what their mission statement was and what they repeatedly claimed to be the “right way” to do it.” 🔥🔥🔥 medium.com/@aleksipietiki… Interesting post on AlphaStar's APM and superhuman actions.

I love this series from Human Progress. I wish I could have met Norman Borlaug, a Nobel Peace Prize laureate whose work in agriculture has greatly influenced my thinking. b-gat.es/2HCHL2C

For differentiable problems, there’s backpropagation. For everything else, there’s RL.

Greg Brockman Not quite right. A more accurate statement would be "for everything else, there is gradient-free (zeroth-order) optimization." RL is when there is a sequential decision process and what you see depends on previous actions you took.

Join our Spinning Up in Deep RL Workshop starting at 9amPT via livestream: youtube.com/watch?v=fdY7dt…

In a collaboration with Google Brain, we are releasing the Hanabi Learning Environment: a testbed for collaborative multi-agent learning and theory of mind in the card game Hanabi. Paper: arxiv.org/abs/1902.00506 GitHub: github.com/deepmind/hanab…

*bookmarked* en.m.wikipedia.org/wiki/AI_effect

At a time when bad news seems to dominate the headlines every day, I want to keep reminding people that life is getting better for millions in the world’s poorest countries, thanks in part to smart investments in health.

If you’re a social scientist, please consider applying to OpenAI!

We’re releasing a Neural MMO — a massively multiagent game environment that supports numerous populations of agents: blog.openai.com/neural-mmo/ - Code: github.com/openai/neural-… - 3D Client: github.com/jsuarez5341/ne…

Video of Lecture 3 of CS294-158 Deep Unsupervised Learning is now up! youtu.be/NCRzGmM1ywE We cover: - Flow Models: NICE, RealNVP, AF, neural AF, IAF, Glow, Flow++ (ctd) - Latent Variable Models: VAE

Announcing the BAIR Open Research Commons @Berkeley_AI UC Berkeley to accelerate cutting-edge collaborative AI research with founding sponsors @Amazon, @Facebook, Google, Samsung Electronics, and @WaveComputing! bair.berkeley.edu/blog/2019/03/2…