Tianwei Ni

sample efficiency (2) transformer architecture (1) reinforcement learning (1) imitation learning (1) policy learning (1) inverse reinforcement learning (1) partially observable markov decision process (1) boundary detection (1) reward function (1) collision avoidance (1) recurrent neural network (1) 3d segmentation (1) model-free reinforcement learning (1) credit assignment (1) 3d medical image segmentation (1) auxiliary task (1) long-term dependency (1) recurrent model-free reinforcement learning (1) memory-based architecture (1) asymptotic performance (1)