Kwei-Herng Lai

reinforcement learning (3) automated machine learning (2) continuous control (2) anomaly detection (1) knowledge distillation (1) policy learning (1) video understanding (1) outlier detection (1) time series (1) off-policy learning (1) collaborative learning (1) hyperparameter tuning (1) feature engineering (1) recommender system (1) device placement (1) distributed system (1) imperfect information game (1) experience replay optimization (1) replay policy (1) policy distillation (1)