Dongsoo Har

representation learning (1) contrastive learning (1) reinforcement learning (1) sample efficiency (1) vision transformer (1) computer vision (1) novelty detection (1) document analysis (1) image processing (1) zero-shot reinforcement learning (1) sparse reward (1) hindsight experience replay (1) multi-goal learning (1) robotic control (1) sparse autoencoder (1) attention head (1) cosine similarity (1) bidirectional encoder representations from transformer (1) optical character recognition (1) noise robust (1)