Kaixuan Chen

multi-agent reinforcement learning (3) activity recognition (2) offline reinforcement learning (2) contrastive learning (2) knowledge distillation (1) interpretable machine learning (1) non-convex optimization (1) attention mechanism (1) semi-supervised learning (1) graph representation learning (1) domain adaptation (1) distributed learning (1) prompt learning (1) model merging (1) sensor fusion (1) policy optimization (1) sharpness-aware minimization (1) graph representation (1) agent communication (1) deep reinforcement learning (1)