Jensen Gao

offline reinforcement learning (1) imitation learning (1) robotic manipulation (1) sequential decision making (1) supervised learning (1) compositional generalization (1) generalization ability (1) offline learning (1) robot manipulation (1) policy training (1) goal-conditioned policy (1) policy transfer (1) policy extraction (1) visual imitation learning (1) data collection strategy (1) distance weighted supervised learning (1) demonstration datum (1)