Pinzhuo Tian

deep reinforcement learning (1) contrastive learning (1) semantic segmentation (1) few-shot learning (1) spectral clustering (1) domain adaptation (1) scene understanding (1) feature embedding (1) nash equilibrium (1) counterfactual regret minimization (1) pixel classification (1) regret bound (1) extensive-form game (1) model-free method (1) object-centric learning (1) slot attention (1) few-shot semantic segmentation (1) gradient-based meta-learning (1) model-free learning (1) imperfect information game (1)