Aviv Tamar

Unsupervised Feature Learning for Manipulation with Contrastive Domain\n Randomization

2021 · arXiv (Cornell University)

Robotic tasks such as manipulation with visual inputs require image features\nthat capture the physical properties of the scene, e.g., the position and\nconfiguration of objects. Recently, it has been suggested to learn such\nfeatures in an unsupervised …

Goal-Conditioned Supervised Learning with Sub-Goal Prediction

2023 · arXiv (Cornell University)

Recently, a simple yet effective algorithm -- goal-conditioned supervised-learning (GCSL) -- was proposed to tackle goal-conditioned reinforcement-learning. GCSL is based on the principle of hindsight learning: by observing states visited in previously executed trajectories and …