Mel Vecerik

deep reinforcement learning (1) reinforcement learning (1) offline reinforcement learning (1) imitation learning (1) robotic manipulation (1) motion estimation (1) self-supervised learning (1) video understanding (1) robot learning (1) video tracking (1) reward function (1) batch reinforcement learning (1) visual representation learning (1) offline learning (1) reward learning (1) robot manipulation (1) correspondence matching (1) learning from demonstration (1) multi-view consistency (1) trajectory estimation (1)