Nico Gürtler

causal inference (1) deep reinforcement learning (1) motion planning (1) reinforcement learning (1) imitation learning (1) policy optimization (1) positive unlabeled learning (1) hierarchical reinforcement learning (1) value function (1) variance reduction (1) offline learning (1) temporal abstraction (1) temporal difference (1) advantage estimation (1) robotics manipulation (1) actor-critic method (1) sample-efficient learning (1) causal representation (1) subgoal planning (1) long-horizon task (1)