Yazhe Niu

multi-agent reinforcement learning (1) offline reinforcement learning (1) policy optimization (1) sequential decision making (1) flow matching (1) value function (1) model-based reinforcement learning (1) sequential decision (1) score matching (1) monte carlo tree search (1) unsupervised representation learning (1) generative model (1) cooperative learning (1) cooperative multi-agent (1) discriminative task (1) task automation (1) feature extractor (1) ai agent (1) natural language instruction (1) q-value estimation (1)