Philippe Cudré-Mauroux

active learning (1) reinforcement learning (1) variational inference (1) bayesian learning (1) bayesian inference (1) sparse coding (1) text classification (1) attention mechanism (1) policy learning (1) vector quantization (1) event detection (1) sequential prediction (1) hidden state (1) recurrent neural network (1) atari game (1) human-ai interaction (1) human mobility (1) compact state representation (1) policy approximation (1) human rationale (1)