Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees

no code implementations • 16 Jul 2018 • Guiliang Liu, Oliver Schulte, Wang Zhu, Qingcan Li

An LMUT is learned using a novel on-line algorithm that is well-suited for an active play setting, where the mimic learner observes an ongoing interaction between the neural net and the environment.

reinforcement-learning Reinforcement Learning (RL)