Iou-Jen Liu

deep reinforcement learning (4) multi-agent reinforcement learning (2) reinforcement learning (2) sample efficiency (1) imitation learning (1) knowledge distillation (1) visual navigation (1) embodied ai (1) privileged information (1) deep neural network (1) sparse reward (1) training stability (1) policy transfer (1) query language (1) permutation invariance (1) policy distillation (1) external knowledge (1) coordinated exploration (1) cooperative multi-agent exploration (1) normalized entropy (1)