We just released our scientific analysis of OpenAI Five: nitter.vloup.ch/OpenAI/status/12… We are already using findings from Five in other systems at OpenAI like Dactyl (openai.com/blog/solving-rubi…) or our multi-agent work (openai.com/blog/emergent-too…). Hope that others find the results useful!

Solving Rubik’s Cube with a robot hand

We’ve trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand. The neural networks are trained entirely in simulation, using the same reinforcement learning code...

openai.com
OpenAI
 @OpenAI
13 Dec 2019
We're releasing "Dota 2 with Large Scale Deep Reinforcement Learning", a scientific paper analyzing our findings from our 3-year Dota project: openai.com/projects/five/ One highlight — we trained a new agent, Rerun, which has a 98% win rate vs the version that beat @OGEsports.

Dec 13, 2019 · 5:56 PM UTC

2
16
2
75
Replying to @gdb
Again, sincere congratulations on this fantastic work.
Replying to @gdb
Could you elaborate on which parts were applied to other systems? I'm guessing Rapid and Surgery? Great work, either way, thank you for sharing!