Sergey Levine

Computer scientist at the University of California, Berkeley, and a co-founder of the robotics company Physical IntelligencePhysical Intelligence, prop. n.: A San Francisco company, founded in 2024, that builds general-purpose AI 'brains' meant to control many different kinds of robots doing many different tasks. (2024), among the most prolific researchers in robot learningrobot learning, n.: Teaching robots skills from data and experience, such as watching demonstrations, practicing by trial and error or training in simulation, instead of programming every movement by hand. and deep reinforcement learningdeep reinforcement learning, n.: Reinforcement learning in which a large neural network does the learning, letting an AI learn tasks such as video games or robot control directly from raw inputs like screen pixels or camera images.. With Chelsea FinnChelsea Finn, prop. n.: An American computer scientist at Stanford known for 'learning to learn' methods that let AI adapt to new tasks from a few examples, and a co-founder of the robotics company Physical Intelligence., Trevor Darrell and Pieter AbbeelPieter Abbeel, prop. n.: A Belgian-American roboticist at Berkeley whose research taught robots to learn from demonstrations and from trial and error, and who co-founded the robotics company Covariant. he showed that robots could learn visuomotor control end to end, mapping camera images directly to motor commands with deep networks (2015–2016), and at Google he ran large-scale grasping experiments on 14 robot arms (2016). He co-authored trust region policy optimizationtrust region policy optimization, n.: A method for improving an AI's strategy in careful steps, never changing it too much at once, so that a single bad update cannot wreck what it has already learned., generalized advantage estimationgeneralized advantage estimation, n.: A recipe for judging how much better each action was than expected by blending short-term and long-term evidence, trading a little accuracy for much steadier learning., soft actor–criticsoft actor–critic, n.: A method for training AI agents, popular in robotics, that rewards the agent both for succeeding and for keeping its behavior varied, which helps it explore and learn reliably from reused experience. (2018) and model-agnostic meta-learningmodel-agnostic meta-learning, n.: A training method that searches for a starting point for a model's internal settings from which it can learn any new task of a given kind with just a few small adjustments., helped define offline reinforcement learningoffline reinforcement learning, n.: Learning a strategy entirely from a fixed collection of recorded experience — logs, past robot runs, medical records — without trying anything new in the real world while learning. through a widely used 2020 review and methods such as conservative Q-learning, and worked on sim-to-real transfersim-to-real transfer, n.: Training a robot's AI in a computer simulation, where practice is fast, cheap and safe, and then making it work on the real robot despite the differences between simulation and reality. and action chunkingaction chunking, n.: Having a robot's AI plan a short burst of upcoming movements, say the next second, all at once instead of one tiny motion at a time, which makes motion smoother and mistakes rarer.. Physical Intelligence's π0π0, prop. n.: A general-purpose AI model for controlling robots, released in 2024 by the start-up Physical Intelligence, that sees through cameras, follows typed or spoken instructions and moves robot arms deftly enough to fold laundry. (2024) and its successors are leading vision-language-action modelsvision-language-action model, n.: An AI model that looks through a robot's cameras, reads an instruction such as 'put the cup in the sink', and turns both straight into the robot's movements..