Introspection-based Explainable Reinforcement Learning in Episodic and Non-episodic Scenarios

no code implementations • 23 Nov 2022 • Niclas Schroeter, Francisco Cruz, Stefan Wermter

Results obtained show the viability of introspection for episodic robotics tasks and, additionally, that the introspection-based approach can be used to generate explanations for the actions taken in a non-episodic robotics environment as well.

reinforcement-learning Reinforcement Learning (RL)