current
last updated
curious about
what transfers when a policy moves to an environment it hasn't seen, and whether reliability comes from better policies or from the system built around them
building
corrective rl environments for robots, task routers within action policies, and turning failure into training data. systems that help robots ship to production reliably
reading
just finished delivering happiness by tony hsieh. now reading the infinite game by simon sinek
training for
a full marathon in bombay on january 18th. trying to get my weekly mileage up