Thomas Lampe

reinforcement learning (3) robot manipulation (3) multi-task learning (2) transfer learning (2) policy optimization (2) off-policy learning (2) deep reinforcement learning (2) offline reinforcement learning (2) apprenticeship learning (1) robot control (1) model-based reinforcement learning (1) continuous control (1) model-free reinforcement learning (1) optimal control (1) continuous action space (1) temporal abstraction (1) hierarchical reinforcement learning (1) fluid dynamics (1) compositional learning (1) robotic manipulation (1)