im releasing all my agent skills to the public
this is hundreds of hours of trial & error
every single global .agents skill i have
go grab it. it's free.
@RoboPapers@IgentixAi@KeithJDeCesare S1 is just the beginning. In context, long-horizon, generalized learning is possible, but can it worked air-gapped?
Reinforcement learning has unlocked tremendous gains in broader AI and humanoid robot whole body control, but still has yet to deliver strong results for robot manipulation due to the difficulty of capturing tasks in an accurate simulation; one way to fix this is to create complex environments with learned world models. But learning fully within world models is often intractable as powerful world models are computationally too expensive.
Instead, @Jsphamigo and @Rk4342R propose to break the problem down: into a large-scale world model that can generate forward trajectories, and a lightweight, low-dimensional latent-space model which can approximate local dynamics of a problem, without needing to back-propagate through a heavy global model. What this means: you can do reinforcement learning in this coupled local-global world model, and learn contact rich skills for a robot.
To learn more, watch Episode #101 of RoboPapers, with @micoolcho and @DJiafei!
Learn contact-rich humanoid manipulation policies, purely within a world model. This is usually not tractable, because you need a very large model to get the contact dynamics right -- instead, @Jsphamigo@Rk4342R couple a large global model with a local model. Very cool work on @RoboPapers ->
Introducing S1, our new foundation model that learns from one example.
It can be taught 10-minute long tasks that it has never seen before, from one video prompt without any fine-tuning.
Watch S1 operate in real-time via in-context learning:
This is #BridgingTomorrow to learn about environmental stewardship and caring for creation. Every plant sprouts from a seed of creation. @CnDelarosa in NYC @NYCParks do you care?
https://t.co/TjUS6WBoVW
"Nature Learning" @InwoodButterfly provides true hands-on up close and personal empathy building experience #BridgingTomorrow#wegrowlife children raise adult monarch butterflies to save an endangered migration. #MuskQuest
Graph engineering acts as the operational framework for these models. While a world model provides the 'internal logic' or simulation of a domain, the graph provides the system architecture to apply that logic. #BridgingTomorrow@IgentixAi@InwoodReporter
https://t.co/jIZUXnm7wc
@UltraSkool1 Orch-OR is THE bridge between quantum gravity, biology, and the phenomenology of mind.
The sum of individual reductions are the building blocks of our reality.
Consciousness is not a byproduct of matter....it is a fundamental feature of the architecture itself.