Yuxuan Zheng

large language model (2) multi-agent reinforcement learning (1) offline reinforcement learning (1) transfer learning (1) autonomous agent (1) diverse policy (1) long-horizon planning (1) text-attributed graph (1) centralized training decentralized execution (1) open-world learning (1) graph neural network (1) offline multi-agent reinforcement learning (1) policy agreement (1) autoregressive decision-making (1) diverse joint policy (1) skill library (1) representation learning (1) cooperative policy (1)