Imagine WWE SmackDown, but with cute, AI-trained robots. Eight teams spend days training reinforcement-learning policies for Pollen’s open-source MicroDuck, then we throw them in the simulator to fight for the Golden Beak Belt. The whole competition will be livestreamed. The catch: you’re not building a robot, you’re training its brain. Want in? Register a team, train your policy, or host a showdown in your city. When the real MicroDucks ship, we go IRL.
This is the most fun use of reinforcement learning I've seen on here in a while - turning an RL leaderboard into an actual spectator sport is a genuinely good idea. Are the policies trained from scratch each competition or can teams carry over and fine-tune a duck across seasons?
@picsoung training a duck to fight is not what i expected to see today 😂
curious what’s been the most unexpected strategy someone has tried so far?
Dial
This is the most fun use of reinforcement learning I've seen on here in a while - turning an RL leaderboard into an actual spectator sport is a genuinely good idea. Are the policies trained from scratch each competition or can teams carry over and fine-tune a duck across seasons?