reinforcement learning

“It turns out to be like pretty straightforward to go in and like find all those pauses and remove them. And you can speed things up further, so you can get a task where a person demonstrates what it means to succeed, and then you can have the robot practice th…”

“So, I think the big challenge, and this is kind of what I'm leaning up to, and what I hope to, ah, that we'll figure out here at Physical Intelligence is how to combine those threads. How to bring in all of that knowledge that you get with generative AI, but a…”

“And for example, we had this demo on, ah, making espresso. That system practiced making those espressos many, many times and used that to improve robustness, improve speed, improve throughput.”

“So the environments can get more and more complex, and those environments run on CPUs. They don't run on GPUs. They don't run on ASICs. The ASICs run the model,”

“If we're doing reinforcement learning on the model, it's basically inference within a sandbox with a reward function, right? And so if the model's better at more efficient inference, that RL is more efficient as well.”