Sim-to-real learning for humanoid robots is a full-stack problem. Today, Amazon FAR is releasing a full-stack solution: Holosoma.
To accelerate research, we are open-sourcing a complete codebase covering multiple simulation backends, training, retargeting, and real-world inference.
The Maximal Update Parameterization (µP) allows LR transfer from small to large models, saving costly tuning. But why is independent weight decay (IWD) essential for it to work?
We find µP stabilizes early training (like an LR warmup), but IWD takes over in the long term! 🧵
Our robotics team will be at ICRA next week in Atlanta! Having started a new research team at Amazon building robot foundation models, we're hiring across all levels, full-time or intern, and across both SW and Research roles. Ping me at [email protected] and let's have a chat!
There is perhaps no better demonstration of the folly of human conceits than this distant image of our tiny world. To me, it underscores our responsibility to deal more kindly with one another and to preserve and cherish the pale blue dot, the only home w…https://t.co/B7raB2U4pJ
United in Enthusiasm and Growth | Our team's collective energy is fueled by the power of learning, growth and Inclusivity. Together, we embrace challenges, inspire one another, and foster a culture of Inclusion & Collaboration. With each team-learning ses…https://t.co/MULhKc5N9p