Joseph J Lim

imitation learning (3) robot manipulation (3) long-horizon planning (2) adversarial learning (1) model-based reinforcement learning (1) domain adaptation (1) offline reinforcement learning (1) knowledge distillation (1) domain randomization (1) message passing (1) temporal abstraction (1) generalization ability (1) skill chaining (1) stream-based learning (1) scalable learning (1) semi-supervised learning (1) policy training (1) policy transfer (1) sample efficiency (1) reinforcement learning (1)