Montserrat Gonzalez Arenas

deep reinforcement learning (1) sequence modeling (1) zero-shot learning (1) sim-to-real transfer (1) robotic manipulation (1) domain generalization (1) in-context learning (1) model predictive control (1) robot control (1) reward function (1) end-to-end learning (1) pattern completion (1) robotic control (1) semantic reasoning (1) vision-language-action model (1) chain of thought reasoning (1) closed-loop control (1) mobile manipulator (1) quadruped robot (1) language interface (1)