Sergey LevineSergey Levine
UC Berkeley / Physical Intelligence
Robot Learning PioneerRobot Learning Pioneer
rlembodied
UC Berkeley professor who developed end-to-end robot learning from raw pixels. His work demonstrated that robots could learn complex manipulation tasks directly from visual input using deep reinforcement learning, without hand-engineered features. Key contributor to offline RL (learning from pre-collected datasets rather than online interaction). Co-founded Physical Intelligence (pi), a company building foundation models for robotics. His research bridges the gap between the success of large language models and the physical world.
UC Berkeley professor who developed end-to-end robot learning from raw pixels. His work demonstrated that robots could learn complex manipulation tasks directly from visual input using deep reinforcement learning, without hand-engineered features. Key contributor to offline RL (learning from pre-collected datasets rather than online interaction). Co-founded Physical Intelligence (pi), a company building foundation models for robotics. His research bridges the gap between the success of large language models and the physical world.
在关系图谱中查看 Sergey Levine →View Sergey Levine in the graph →
听 Sergey Levine 的 AI 播客 →Listen on AI Podcast →
读 Sergey Levine 的论文与长文 →Read on AI Paper →