Pieter Abbeel

Belgian-American computer scientist at the University of California, Berkeley, a leader of robot learning 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.. As a doctoral student of Andrew NgAndrew Ng, prop. n.: A British-born American computer scientist whose online courses have taught machine learning to millions; he also co-founded Google's deep learning team, Google Brain, and the online-course company Coursera. at Stanford he developed apprenticeship learning via inverse reinforcement learninginverse reinforcement learning, n.: Working backward from behavior to goals: watching an expert act and inferring what they must be trying to achieve, so an AI can pursue the same aims. (2004), which let an autonomous helicopter learn aerobatic maneuvers from expert pilots. At Berkeley his group co-developed 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., 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. (with Chelsea Finn and Sergey Levine, 2017), domain randomizationdomain randomization, n.: Training a robot's AI in a simulation whose colors, lighting, weights, friction and other details are shuffled at random on every run, so that the real world holds few surprises it has not already practiced for. for 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 the denoising diffusion probabilistic modeldenoising diffusion probabilistic model, n.: The 2020 recipe that made diffusion image generators work well: add noise to pictures over a thousand small steps, then train a network to guess the noise so it can be removed. (with Jonathan Ho and Ajay Jain, 2020); with Stuart RussellStuart Russell, prop. n.: A British computer scientist who co-wrote the standard AI textbook and argues that AI must be redesigned to stay uncertain about what humans want, so that it remains under human control. he helped found the Center for Human-Compatible AICenter for Human-Compatible AI, prop. n.: Stuart Russell's group at the University of California, Berkeley, which argues that AI should be built to be unsure of what people want and to learn it by watching them.. He co-founded the grading platform Gradescope and the robotics company Covariant (2017), whose founders joined Amazon under a licensing deal in 2024; in December 2025 Amazon put him in charge of large-language-model work within its AGI organization. He received the ACM Prize in Computing (2021).