Jifeng Hu

deep reinforcement learning (1) transformer architecture (1) multi-agent reinforcement learning (1) sequence modeling (1) reinforcement learning (1) policy optimization (1) domain generalization (1) in-context learning (1) policy learning (1) visual reinforcement learning (1) saliency map (1) reward uncertainty (1) state space model (1) decision transformer (1) long-term memory (1) mamba model (1) reward estimation (1) feature decorrelation (1) sample reweighting (1) reward aggregation (1)