Johannes Fürnkranz

multi-label classification (2) preference-based reinforcement learning (2) neural machine translation (1) text summarization (1) policy learning (1) exploration exploitation (1) multi-class classification (1) label prediction (1) greedy selection (1) rule learning (1) recurrent neural network (1) reward shaping (1) trajectory feedback (1) monte carlo method (1) label dependency (1) model-free learning (1) q-value estimation (1) pairwise classification (1) classifier chain (1) translation quality (1)