Towards Explanatory Interactive Reinforcement Learning for Aligned and Trustworthy Agents


Recording of a talk delivered to fellow Bristol researchers on 18/01/21, as part of a one-day symposium on Combining Knowledge and Data.

A brief overview of my AAAI 2021 paper (TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments) and plans for future work.