Achieving efficient interpretability of reinforcement learning via policy distillation and selective input gradient regularization
Jinwei Xing, Takashi Nagata, Xinyun Zou, Emre Neftci, Jeffrey L. Krichmar
Topics & Concepts
InterpretabilityReinforcement learningComputer scienceArtificial intelligenceMachine learningRobustness (evolution)Regularization (linguistics)DistillationArtificial neural networkDeep neural networksOrganic chemistryGeneChemistryBiochemistryAdversarial Robustness in Machine LearningReinforcement Learning in RoboticsExplainable Artificial Intelligence (XAI)