Junge Zhang

multi-agent reinforcement learning (4) policy gradient (3) zero-shot learning (3) multi-agent system (3) reinforcement learning (3) sparse reward (3) large language model (2) domain shift (2) image cropping (2) backdoor attack (2) model-based reinforcement learning (2) dynamics model (2) markov random field (2) transductive learning (2) domain adaptation (2) computer vision (2) embedding space (2) uncertainty quantification (2) energy minimization (2) multi-task learning (1)