Really interesting results here! Agents showed the ability to organize and collaborate without explicit reward pressure. Thanks again to @thinkymachines and @cHHillee for the credits!
1/ We taught a team of Inkling 2 Small agents to work together, communicate, and delegate work, without predefined roles on hard chess puzzles. Using our simple multi-agent RL recipe, we are able to turn pass@k into pass@1.
Work with @emilianogl and @GabeVisotsky
🧵