Pieter AbbeelPieter Abbeel
UC Berkeley / Covariant
机器人学与强化学习先驱Robotics & RL Pioneer
rl
生于比利时。斯坦福大学博士（2008，导师 Andrew Ng），论文研究学徒学习和逆强化学习。加入 UC Berkeley 任教，是机器人学习和深度强化学习领域的重要研究者。实验室提出了 Sim-to-Real 迁移（在模拟中训练机器人、在真实世界中部署）和域随机化技术。创办 Covariant（仓库机器人 AI），将深度学习带入工业机器人领域。指导了 John Schulman 的博士研究（PPO 的创造者）。通过 Berkeley 实验室培养了大量杰出 AI 研究者。
Born in Belgium. Earned his PhD from Stanford under Andrew Ng (2008), with a thesis on apprenticeship learning and inverse reinforcement learning. Joined UC Berkeley as a professor where he became a leading figure in robot learning and deep reinforcement learning. His lab developed sim-to-real transfer (training robots in simulation and deploying in the real world) and domain randomization. Founded Covariant (AI for warehouse robot arms), bringing deep learning to industrial robotics. Advised John Schulman's PhD (the creator of PPO). Has trained numerous prominent AI researchers through his Berkeley lab.
在关系图谱中查看 Pieter Abbeel →View Pieter Abbeel in the graph →