Takayuki Osa

active learning (1) deep reinforcement learning (1) reinforcement learning (1) sample efficiency (1) multi-task learning (1) policy optimization (1) trajectory prediction (1) incremental learning (1) gaussian process (1) value function (1) continuous control (1) model-based reinforcement learning (1) bellman error (1) robot manipulation (1) surgical robotics (1) meta reinforcement learning (1) conditional expectation (1) trajectory planning (1) error distribution (1) dynamic environment (1)