Marcel Torne Villasevil

reinforcement learning (3) policy learning (2) imitation learning (1) sim-to-real transfer (1) robotic navigation (1) self-supervised learning (1) human-in-the-loop learning (1) robot manipulation (1) human feedback (1) autonomous reinforcement learning (1) exploration strategy (1) digital twin (1) data collection (1) goal-directed policy (1) goal-conditioned exploration (1) continual learning (1)