We just released our scientific analysis of OpenAI Five: https://twitter.com/OpenAI/status/1205541134925099008 … We are already using findings from Five in other systems at OpenAI like Dactyl (https://openai.com/blog/solving-rubiks-cube/ …) or our multi-agent work (https://openai.com/blog/emergent-tool-use/ …). Hope that others find the results useful!
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!