Yuankun Jiang

Robotics (1)

deep reinforcement learning (2) reinforcement learning (1) sample efficiency (1) robust optimization (1) policy optimization (1) transfer learning (1) domain randomization (1) robot control (1) value function estimation (1) worst-case performance (1) off-policy learning (1) robust policy optimization (1) meta-reinforcement learning (1) sparse reward (1) policy generalization (1) camera control (1) importance weight (1) model discrepancy (1) actor-critic framework (1) expert trajectory regularization (1)