TY - CONF T2 - ECML Workshop on Reinforcement Learning with Generalized Feedback: Beyond Numeric Rewards ID - publicatio3836 AV - public UR - http://publicatio.bibl.u-szeged.hu/3836/ A1 - Weng Paul A1 - Busa-Fekete Róbert A1 - Hüllermeier Eyke Y1 - 2013/// TI - Interactive Q-learning with ordinal rewards and unreliable tutor ER -